> ## Documentation Index > Fetch the complete documentation index at: https://docs.cozmox.cloud/llms.txt > Use this file to discover all available pages before exploring further. # List Campaigns ## OpenAPI ````yaml get /campaign openapi: 3.0.0 info: title: cozmox API description: Voice AI for developers. version: '1' contact: {} servers: - description: Cozmox APIs url: https://api.cozmox.ai - url: https://api.cozmox.ai security: [] tags: [] paths: /campaign: get: tags: - Campaigns summary: List Campaigns operationId: CampaignController_findAll parameters: - name: id required: false in: query schema: type: string - name: status required: false in: query schema: enum: - scheduled - in-progress - ended type: string - name: page required: false in: query description: This is the page number to return. Defaults to 1. schema: minimum: 1 type: number - name: sortOrder required: false in: query description: This is the sort order for pagination. Defaults to 'DESC'. schema: enum: - ASC - DESC type: string - name: limit required: false in: query description: This is the maximum number of items to return. Defaults to 100. schema: minimum: 0 maximum: 1000 type: number - name: createdAtGt required: false in: query description: >- This will return items where the createdAt is greater than the specified value. schema: format: date-time type: string - name: createdAtLt required: false in: query description: >- This will return items where the createdAt is less than the specified value. schema: format: date-time type: string - name: createdAtGe required: false in: query description: >- This will return items where the createdAt is greater than or equal to the specified value. schema: format: date-time type: string - name: createdAtLe required: false in: query description: >- This will return items where the createdAt is less than or equal to the specified value. schema: format: date-time type: string - name: updatedAtGt required: false in: query description: >- This will return items where the updatedAt is greater than the specified value. schema: format: date-time type: string - name: updatedAtLt required: false in: query description: >- This will return items where the updatedAt is less than the specified value. schema: format: date-time type: string - name: updatedAtGe required: false in: query description: >- This will return items where the updatedAt is greater than or equal to the specified value. schema: format: date-time type: string - name: updatedAtLe required: false in: query description: >- This will return items where the updatedAt is less than or equal to the specified value. schema: format: date-time type: string responses: '200': description: '' content: application/json: schema: $ref: '#/components/schemas/CampaignPaginatedResponse' security: - bearer: [] components: schemas: CampaignPaginatedResponse: type: object properties: results: type: array items: $ref: '#/components/schemas/Campaign' metadata: $ref: '#/components/schemas/PaginationMeta' required: - results - metadata Campaign: type: object properties: status: type: string description: This is the status of the campaign. enum: - scheduled - in-progress - ended endedReason: type: string description: This is the explanation for how the campaign ended. enum: - campaign.scheduled.ended-by-user - campaign.in-progress.ended-by-user - campaign.ended.success name: type: string description: >- This is the name of the campaign. This is just for your own reference. example: Q2 Sales Campaign assistantId: type: string description: >- This is the assistant ID that will be used for the campaign calls. Note: Either assistantId or workflowId can be used, but not both. workflowId: type: string description: >- This is the workflow ID that will be used for the campaign calls. Note: Either assistantId or workflowId can be used, but not both. phoneNumberId: type: string description: >- This is the phone number ID that will be used for the campaign calls. schedulePlan: description: This is the schedule plan for the campaign. allOf: - $ref: '#/components/schemas/SchedulePlan' customers: description: These are the customers that will be called in the campaign. type: array items: $ref: '#/components/schemas/CreateCustomerDTO' id: type: string description: This is the unique identifier for the campaign. orgId: type: string description: >- This is the unique identifier for the org that this campaign belongs to. createdAt: format: date-time type: string description: >- This is the ISO 8601 date-time string of when the campaign was created. updatedAt: format: date-time type: string description: >- This is the ISO 8601 date-time string of when the campaign was last updated. calls: type: object description: This is a map of call IDs to campaign call details. callsCounterScheduled: type: number description: This is the number of calls that have been scheduled. callsCounterQueued: type: number description: This is the number of calls that have been queued. callsCounterInProgress: type: number description: This is the number of calls that have been in progress. callsCounterEndedVoicemail: type: number description: This is the number of calls whose ended reason is 'voicemail'. callsCounterEnded: type: number description: This is the number of calls that have ended. required: - status - name - phoneNumberId - customers - id - orgId - createdAt - updatedAt - calls - callsCounterScheduled - callsCounterQueued - callsCounterInProgress - callsCounterEndedVoicemail - callsCounterEnded PaginationMeta: type: object properties: itemsPerPage: type: number totalItems: type: number currentPage: type: number required: - itemsPerPage - totalItems - currentPage SchedulePlan: type: object properties: earliestAt: format: date-time type: string description: >- This is the ISO 8601 date-time string of the earliest time the call can be scheduled. latestAt: format: date-time type: string description: >- This is the ISO 8601 date-time string of the latest time the call can be scheduled. required: - earliestAt CreateCustomerDTO: type: object properties: numberE164CheckEnabled: type: boolean description: >- This is the flag to toggle the E164 check for the `number` field. This is an advanced property which should be used if you know your use case requires it. Use cases: - `false`: To allow non-E164 numbers like `+001234567890`, `1234`, or `abc`. This is useful for dialing out to non-E164 numbers on your SIP trunks. - `true` (default): To allow only E164 numbers like `+14155551234`. This is standard for PSTN calls. If `false`, the `number` is still required to only contain alphanumeric characters (regex: `/^\+?[a-zA-Z0-9]+$/`). @default true (E164 check is enabled) default: true extension: type: string description: >- This is the extension that will be dialed after the call is answered. maxLength: 10 example: null assistantOverrides: description: >- These are the overrides for the assistant's settings and template variables specific to this customer. This allows customization of the assistant's behavior for individual customers in batch calls. allOf: - $ref: '#/components/schemas/AssistantOverrides' number: type: string description: This is the number of the customer. minLength: 3 maxLength: 40 sipUri: type: string description: This is the SIP URI of the customer. name: type: string description: >- This is the name of the customer. This is just for your own reference. For SIP inbound calls, this is extracted from the `From` SIP header with format `"Display Name" `. maxLength: 40 email: type: string description: This is the email of the customer. maxLength: 40 externalId: type: string description: This is the external ID of the customer. maxLength: 40 AssistantOverrides: type: object properties: transcriber: description: These are the options for the assistant's transcriber. oneOf: - $ref: '#/components/schemas/AssemblyAITranscriber' title: AssemblyAITranscriber - $ref: '#/components/schemas/AzureSpeechTranscriber' title: AzureSpeechTranscriber - $ref: '#/components/schemas/CustomTranscriber' title: CustomTranscriber - $ref: '#/components/schemas/DeepgramTranscriber' title: DeepgramTranscriber - $ref: '#/components/schemas/ElevenLabsTranscriber' title: ElevenLabsTranscriber - $ref: '#/components/schemas/GladiaTranscriber' title: GladiaTranscriber - $ref: '#/components/schemas/GoogleTranscriber' title: GoogleTranscriber - $ref: '#/components/schemas/SpeechmaticsTranscriber' title: SpeechmaticsTranscriber - $ref: '#/components/schemas/TalkscriberTranscriber' title: TalkscriberTranscriber - $ref: '#/components/schemas/OpenAITranscriber' title: OpenAITranscriber - $ref: '#/components/schemas/CartesiaTranscriber' title: CartesiaTranscriber model: description: These are the options for the assistant's LLM. oneOf: - $ref: '#/components/schemas/AnthropicModel' title: Anthropic - $ref: '#/components/schemas/AnyscaleModel' title: Anyscale - $ref: '#/components/schemas/CerebrasModel' title: Cerebras - $ref: '#/components/schemas/CustomLLMModel' title: CustomLLM - $ref: '#/components/schemas/DeepInfraModel' title: DeepInfra - $ref: '#/components/schemas/DeepSeekModel' title: DeepSeek - $ref: '#/components/schemas/GoogleModel' title: Google - $ref: '#/components/schemas/GroqModel' title: Groq - $ref: '#/components/schemas/InflectionAIModel' title: InflectionAI - $ref: '#/components/schemas/OpenAIModel' title: OpenAI - $ref: '#/components/schemas/OpenRouterModel' title: OpenRouter - $ref: '#/components/schemas/PerplexityAIModel' title: PerplexityAI - $ref: '#/components/schemas/TogetherAIModel' title: Together - $ref: '#/components/schemas/XaiModel' title: XAI voice: description: These are the options for the assistant's voice. oneOf: - $ref: '#/components/schemas/AzureVoice' title: AzureVoice - $ref: '#/components/schemas/CartesiaVoice' title: CartesiaVoice - $ref: '#/components/schemas/CustomVoice' title: CustomVoice - $ref: '#/components/schemas/DeepgramVoice' title: DeepgramVoice - $ref: '#/components/schemas/ElevenLabsVoice' title: ElevenLabsVoice - $ref: '#/components/schemas/HumeVoice' title: HumeVoice - $ref: '#/components/schemas/LMNTVoice' title: LMNTVoice - $ref: '#/components/schemas/NeuphonicVoice' title: NeuphonicVoice - $ref: '#/components/schemas/OpenAIVoice' title: OpenAIVoice - $ref: '#/components/schemas/PlayHTVoice' title: PlayHTVoice - $ref: '#/components/schemas/RimeAIVoice' title: RimeAIVoice - $ref: '#/components/schemas/SmallestAIVoice' title: SmallestAIVoice - $ref: '#/components/schemas/TavusVoice' title: TavusVoice - $ref: '#/components/schemas/cozmoxVoice' title: cozmoxVoice - $ref: '#/components/schemas/SesameVoice' title: SesameVoice - $ref: '#/components/schemas/InworldVoice' title: InworldVoice firstMessage: type: string description: >- This is the first message that the assistant will say. This can also be a URL to a containerized audio file (mp3, wav, etc.). If unspecified, assistant will wait for user to speak and use the model to respond once they speak. example: Hello! How can I help you today? firstMessageInterruptionsEnabled: type: boolean default: false firstMessageMode: type: string description: >- This is the mode for the first message. Default is 'assistant-speaks-first'. Use: - 'assistant-speaks-first' to have the assistant speak first. - 'assistant-waits-for-user' to have the assistant wait for the user to speak first. - 'assistant-speaks-first-with-model-generated-message' to have the assistant speak first with a message generated by the model based on the conversation state. (`assistant.model.messages` at call start, `call.messages` at squad transfer points). @default 'assistant-speaks-first' enum: - assistant-speaks-first - assistant-speaks-first-with-model-generated-message - assistant-waits-for-user example: assistant-speaks-first voicemailDetection: description: >- These are the settings to configure or disable voicemail detection. Alternatively, voicemail detection can be configured using the model.tools=[VoicemailTool]. This uses Twilio's built-in detection while the VoicemailTool relies on the model to detect if a voicemail was reached. You can use neither of them, one of them, or both of them. By default, Twilio built-in detection is enabled while VoicemailTool is not. oneOf: - $ref: '#/components/schemas/GoogleVoicemailDetectionPlan' title: Google - $ref: '#/components/schemas/OpenAIVoicemailDetectionPlan' title: OpenAI - $ref: '#/components/schemas/TwilioVoicemailDetectionPlan' title: Twilio - $ref: '#/components/schemas/cozmoxVoicemailDetectionPlan' title: cozmox clientMessages: type: array enum: - conversation-update - function-call - function-call-result - hang - language-changed - metadata - model-output - speech-update - status-update - transcript - tool-calls - tool-calls-result - tool.completed - transfer-update - user-interrupted - voice-input - workflow.node.started example: - conversation-update - function-call - hang - model-output - speech-update - status-update - transfer-update - transcript - tool-calls - user-interrupted - voice-input - workflow.node.started description: >- These are the messages that will be sent to your Client SDKs. Default is conversation-update,function-call,hang,model-output,speech-update,status-update,transfer-update,transcript,tool-calls,user-interrupted,voice-input,workflow.node.started. You can check the shape of the messages in ClientMessage schema. items: type: string enum: - conversation-update - function-call - function-call-result - hang - language-changed - metadata - model-output - speech-update - status-update - transcript - tool-calls - tool-calls-result - tool.completed - transfer-update - user-interrupted - voice-input - workflow.node.started serverMessages: type: array enum: - conversation-update - end-of-call-report - function-call - hang - language-changed - language-change-detected - model-output - phone-call-control - speech-update - status-update - transcript - transcript[transcriptType="final"] - tool-calls - transfer-destination-request - transfer-update - user-interrupted - voice-input example: - conversation-update - end-of-call-report - function-call - hang - speech-update - status-update - tool-calls - transfer-destination-request - user-interrupted description: >- These are the messages that will be sent to your Server URL. Default is conversation-update,end-of-call-report,function-call,hang,speech-update,status-update,tool-calls,transfer-destination-request,user-interrupted. You can check the shape of the messages in ServerMessage schema. items: type: string enum: - conversation-update - end-of-call-report - function-call - hang - language-changed - language-change-detected - model-output - phone-call-control - speech-update - status-update - transcript - transcript[transcriptType="final"] - tool-calls - transfer-destination-request - transfer-update - user-interrupted - voice-input silenceTimeoutSeconds: type: number description: >- How many seconds of silence to wait before ending the call. Defaults to 30. @default 30 minimum: 10 maximum: 3600 example: 30 maxDurationSeconds: type: number description: >- This is the maximum number of seconds that the call will last. When the call reaches this duration, it will be ended. @default 600 (10 minutes) minimum: 10 maximum: 43200 example: 600 backgroundSound: description: >- This is the background sound in the call. Default for phone calls is 'office' and default for web calls is 'off'. You can also provide a custom sound by providing a URL to an audio file. oneOf: - type: string enum: - 'off' - office example: office - type: string format: uri example: https://www.soundjay.com/ambient/sounds/people-in-lounge-1.mp3 backgroundDenoisingEnabled: type: boolean description: >- This enables filtering of noise and background speech while the user is talking. Default `false` while in beta. @default false deprecated: true example: false modelOutputInMessagesEnabled: type: boolean description: >- This determines whether the model's output is used in conversation history rather than the transcription of assistant's speech. Default `false` while in beta. @default false example: false transportConfigurations: type: array description: >- These are the configurations to be passed to the transport providers of assistant's calls, like Twilio. You can store multiple configurations for different transport providers. For a call, only the configuration matching the call transport provider is used. items: oneOf: - $ref: '#/components/schemas/TransportConfigurationTwilio' title: Twilio observabilityPlan: description: |- This is the plan for observability of assistant's calls. Currently, only Langfuse is supported. oneOf: - $ref: '#/components/schemas/LangfuseObservabilityPlan' title: Langfuse allOf: - $ref: '#/components/schemas/LangfuseObservabilityPlan' credentials: type: array description: >- These are dynamic credentials that will be used for the assistant calls. By default, all the credentials are available for use in the call but you can supplement an additional credentials using this. Dynamic credentials override existing credentials. items: oneOf: - $ref: '#/components/schemas/CreateAnthropicCredentialDTO' title: AnthropicCredential - $ref: '#/components/schemas/CreateAnyscaleCredentialDTO' title: AnyscaleCredential - $ref: '#/components/schemas/CreateAssemblyAICredentialDTO' title: AssemblyAICredential - $ref: '#/components/schemas/CreateAzureCredentialDTO' title: AzureCredential - $ref: '#/components/schemas/CreateAzureOpenAICredentialDTO' title: AzureOpenAICredential - $ref: '#/components/schemas/CreateByoSipTrunkCredentialDTO' title: ByoSipTrunkCredential - $ref: '#/components/schemas/CreateCartesiaCredentialDTO' title: CartesiaCredential - $ref: '#/components/schemas/CreateCerebrasCredentialDTO' title: CerebrasCredential - $ref: '#/components/schemas/CreateCloudflareCredentialDTO' title: CloudflareCredential - $ref: '#/components/schemas/CreateCustomLLMCredentialDTO' title: CustomLLMCredential - $ref: '#/components/schemas/CreateDeepgramCredentialDTO' title: DeepgramCredential - $ref: '#/components/schemas/CreateDeepInfraCredentialDTO' title: DeepInfraCredential - $ref: '#/components/schemas/CreateDeepSeekCredentialDTO' title: DeepSeekCredential - $ref: '#/components/schemas/CreateElevenLabsCredentialDTO' title: ElevenLabsCredential - $ref: '#/components/schemas/CreateGcpCredentialDTO' title: GcpCredential - $ref: '#/components/schemas/CreateGladiaCredentialDTO' title: GladiaCredential - $ref: '#/components/schemas/CreateGoHighLevelCredentialDTO' title: GhlCredential - $ref: '#/components/schemas/CreateGoogleCredentialDTO' title: GoogleCredential - $ref: '#/components/schemas/CreateGroqCredentialDTO' title: GroqCredential - $ref: '#/components/schemas/CreateHumeCredentialDTO' title: HumeCredential - $ref: '#/components/schemas/CreateInflectionAICredentialDTO' title: InflectionAICredential - $ref: '#/components/schemas/CreateLangfuseCredentialDTO' title: LangfuseCredential - $ref: '#/components/schemas/CreateLmntCredentialDTO' title: LmntCredential - $ref: '#/components/schemas/CreateMakeCredentialDTO' title: MakeCredential - $ref: '#/components/schemas/CreateMistralCredentialDTO' title: MistralCredential - $ref: '#/components/schemas/CreateNeuphonicCredentialDTO' title: NeuphonicCredential - $ref: '#/components/schemas/CreateOpenAICredentialDTO' title: OpenAICredential - $ref: '#/components/schemas/CreateOpenRouterCredentialDTO' title: OpenRouterCredential - $ref: '#/components/schemas/CreatePerplexityAICredentialDTO' title: PerplexityAICredential - $ref: '#/components/schemas/CreatePlayHTCredentialDTO' title: PlayHTCredential - $ref: '#/components/schemas/CreateRimeAICredentialDTO' title: RimeAICredential - $ref: '#/components/schemas/CreateRunpodCredentialDTO' title: RunpodCredential - $ref: '#/components/schemas/CreateS3CredentialDTO' title: S3Credential - $ref: '#/components/schemas/CreateSmallestAICredentialDTO' title: SmallestAICredential - $ref: '#/components/schemas/CreateSpeechmaticsCredentialDTO' title: SpeechmaticsCredential - $ref: '#/components/schemas/CreateSupabaseCredentialDTO' title: SupabaseCredential - $ref: '#/components/schemas/CreateTavusCredentialDTO' title: TavusCredential - $ref: '#/components/schemas/CreateTogetherAICredentialDTO' title: TogetherAICredential - $ref: '#/components/schemas/CreateTrieveCredentialDTO' title: TrieveCredential - $ref: '#/components/schemas/CreateTwilioCredentialDTO' title: TwilioCredential - $ref: '#/components/schemas/CreateVonageCredentialDTO' title: VonageCredential - $ref: '#/components/schemas/CreateWebhookCredentialDTO' title: WebhookCredential - $ref: '#/components/schemas/CreateXAiCredentialDTO' title: XAiCredential - $ref: >- #/components/schemas/CreateGoogleCalendarOAuth2ClientCredentialDTO title: GoogleCalendarOAuth2ClientCredential - $ref: >- #/components/schemas/CreateGoogleCalendarOAuth2AuthorizationCredentialDTO title: GoogleCalendarOAuth2AuthorizationCredential - $ref: >- #/components/schemas/CreateGoogleSheetsOAuth2AuthorizationCredentialDTO title: GoogleSheetsOAuth2AuthorizationCredential - $ref: >- #/components/schemas/CreateSlackOAuth2AuthorizationCredentialDTO title: SlackOAuth2AuthorizationCredential - $ref: '#/components/schemas/CreateGoHighLevelMCPCredentialDTO' title: GoHighLevelMCPCredential discriminator: propertyName: provider mapping: 11labs: '#/components/schemas/CreateElevenLabsCredentialDTO' anthropic: '#/components/schemas/CreateAnthropicCredentialDTO' anyscale: '#/components/schemas/CreateAnyscaleCredentialDTO' assembly-ai: '#/components/schemas/CreateAssemblyAICredentialDTO' azure-openai: '#/components/schemas/CreateAzureOpenAICredentialDTO' azure: '#/components/schemas/CreateAzureCredentialDTO' byo-sip-trunk: '#/components/schemas/CreateByoSipTrunkCredentialDTO' cartesia: '#/components/schemas/CreateCartesiaCredentialDTO' cerebras: '#/components/schemas/CreateCerebrasCredentialDTO' cloudflare: '#/components/schemas/CreateCloudflareCredentialDTO' custom-llm: '#/components/schemas/CreateCustomLLMCredentialDTO' deepgram: '#/components/schemas/CreateDeepgramCredentialDTO' deepinfra: '#/components/schemas/CreateDeepInfraCredentialDTO' deep-seek: '#/components/schemas/CreateDeepSeekCredentialDTO' gcp: '#/components/schemas/CreateGcpCredentialDTO' gladia: '#/components/schemas/CreateGladiaCredentialDTO' gohighlevel: '#/components/schemas/CreateGoHighLevelCredentialDTO' google: '#/components/schemas/CreateGoogleCredentialDTO' groq: '#/components/schemas/CreateGroqCredentialDTO' inflection-ai: '#/components/schemas/CreateInflectionAICredentialDTO' langfuse: '#/components/schemas/CreateLangfuseCredentialDTO' lmnt: '#/components/schemas/CreateLmntCredentialDTO' make: '#/components/schemas/CreateMakeCredentialDTO' openai: '#/components/schemas/CreateOpenAICredentialDTO' openrouter: '#/components/schemas/CreateOpenRouterCredentialDTO' perplexity-ai: '#/components/schemas/CreatePerplexityAICredentialDTO' playht: '#/components/schemas/CreatePlayHTCredentialDTO' rime-ai: '#/components/schemas/CreateRimeAICredentialDTO' runpod: '#/components/schemas/CreateRunpodCredentialDTO' s3: '#/components/schemas/CreateS3CredentialDTO' supabase: '#/components/schemas/CreateSupabaseCredentialDTO' smallest-ai: '#/components/schemas/CreateSmallestAICredentialDTO' tavus: '#/components/schemas/CreateTavusCredentialDTO' together-ai: '#/components/schemas/CreateTogetherAICredentialDTO' twilio: '#/components/schemas/CreateTwilioCredentialDTO' vonage: '#/components/schemas/CreateVonageCredentialDTO' webhook: '#/components/schemas/CreateWebhookCredentialDTO' xai: '#/components/schemas/CreateXAiCredentialDTO' neuphonic: '#/components/schemas/CreateNeuphonicCredentialDTO' hume: '#/components/schemas/CreateHumeCredentialDTO' mistral: '#/components/schemas/CreateMistralCredentialDTO' speechmatics: '#/components/schemas/CreateSpeechmaticsCredentialDTO' trieve: '#/components/schemas/CreateTrieveCredentialDTO' google.calendar.oauth2-client: >- #/components/schemas/CreateGoogleCalendarOAuth2ClientCredentialDTO google.calendar.oauth2-authorization: >- #/components/schemas/CreateGoogleCalendarOAuth2AuthorizationCredentialDTO google.sheets.oauth2-authorization: >- #/components/schemas/CreateGoogleSheetsOAuth2AuthorizationCredentialDTO slack.oauth2-authorization: >- #/components/schemas/CreateSlackOAuth2AuthorizationCredentialDTO ghl.oauth2-authorization: '#/components/schemas/CreateGoHighLevelMCPCredentialDTO' inworld: '#/components/schemas/CreateInworldCredentialDTO' hooks: type: array description: This is a set of actions that will be performed on certain events. items: oneOf: - $ref: '#/components/schemas/AssistantHookCallEnding' title: AssistantHookCallEnding - $ref: '#/components/schemas/AssistantHookAssistantSpeechInterrupted' title: AssistantHookAssistantSpeechInterrupted - $ref: '#/components/schemas/AssistantHookCustomerSpeechInterrupted' title: AssistantHookCustomerSpeechInterrupted variableValues: type: object description: >- These are values that will be used to replace the template variables in the assistant messages and other text-based fields. This uses LiquidJS syntax. https://liquidjs.com/tutorials/intro-to-liquid.html So for example, `{{ name }}` will be replaced with the value of `name` in `variableValues`. `{{"now" | date: "%b %d, %Y, %I:%M %p", "America/New_York"}}` will be replaced with the current date and time in New York. Some cozmox reserved defaults: - *customer* - the customer object name: type: string description: >- This is the name of the assistant. This is required when you want to transfer between assistants in a call. maxLength: 40 voicemailMessage: type: string description: >- This is the message that the assistant will say if the call is forwarded to voicemail. If unspecified, it will hang up. maxLength: 1000 endCallMessage: type: string description: |- This is the message that the assistant will say if it ends the call. If unspecified, it will hang up without saying anything. maxLength: 1000 endCallPhrases: description: >- This list contains phrases that, if spoken by the assistant, will trigger the call to be hung up. Case insensitive. type: array items: type: string maxLength: 140 minLength: 2 compliancePlan: $ref: '#/components/schemas/CompliancePlan' metadata: type: object description: This is for metadata you want to store on the assistant. backgroundSpeechDenoisingPlan: description: >- This enables filtering of noise and background speech while the user is talking. Features: - Smart denoising using Krisp - Fourier denoising Smart denoising can be combined with or used independently of Fourier denoising. Order of precedence: - Smart denoising - Fourier denoising allOf: - $ref: '#/components/schemas/BackgroundSpeechDenoisingPlan' analysisPlan: description: >- This is the plan for analysis of assistant's calls. Stored in `call.analysis`. allOf: - $ref: '#/components/schemas/AnalysisPlan' artifactPlan: description: >- This is the plan for artifacts generated during assistant's calls. Stored in `call.artifact`. allOf: - $ref: '#/components/schemas/ArtifactPlan' messagePlan: description: >- This is the plan for static predefined messages that can be spoken by the assistant during the call, like `idleMessages`. Note: `firstMessage`, `voicemailMessage`, and `endCallMessage` are currently at the root level. They will be moved to `messagePlan` in the future, but will remain backwards compatible. allOf: - $ref: '#/components/schemas/MessagePlan' startSpeakingPlan: description: >- This is the plan for when the assistant should start talking. You should configure this if you're running into these issues: - The assistant is too slow to start talking after the customer is done speaking. - The assistant is too fast to start talking after the customer is done speaking. - The assistant is so fast that it's actually interrupting the customer. allOf: - $ref: '#/components/schemas/StartSpeakingPlan' stopSpeakingPlan: description: >- This is the plan for when assistant should stop talking on customer interruption. You should configure this if you're running into these issues: - The assistant is too slow to recognize customer's interruption. - The assistant is too fast to recognize customer's interruption. - The assistant is getting interrupted by phrases that are just acknowledgments. - The assistant is getting interrupted by background noises. - The assistant is not properly stopping -- it starts talking right after getting interrupted. allOf: - $ref: '#/components/schemas/StopSpeakingPlan' monitorPlan: description: >- This is the plan for real-time monitoring of the assistant's calls. Usage: - To enable live listening of the assistant's calls, set `monitorPlan.listenEnabled` to `true`. - To enable live control of the assistant's calls, set `monitorPlan.controlEnabled` to `true`. allOf: - $ref: '#/components/schemas/MonitorPlan' credentialIds: description: >- These are the credentials that will be used for the assistant calls. By default, all the credentials are available for use in the call but you can provide a subset using this. type: array items: type: string server: description: >- This is where cozmox will send webhooks. You can find all webhooks available along with their shape in ServerMessage schema. The order of precedence is: 1. assistant.server.url 2. phoneNumber.serverUrl 3. org.serverUrl allOf: - $ref: '#/components/schemas/Server' keypadInputPlan: $ref: '#/components/schemas/KeypadInputPlan' AssemblyAITranscriber: type: object properties: provider: type: string description: This is the transcription provider that will be used. enum: - assembly-ai language: type: string description: This is the language that will be set for the transcription. enum: - en confidenceThreshold: type: number description: |- Transcripts below this confidence threshold will be discarded. @default 0.4 minimum: 0 maximum: 1 example: 0.4 enableUniversalStreamingApi: type: boolean description: >- Uses Assembly AI's new Universal Streaming API. See: https://www.assemblyai.com/docs/speech-to-text/universal-streaming @default false example: false formatTurns: type: boolean description: >- This enables formatting of transcripts. Only used when `enableUniversalStreamingApi` is true. @default false example: false endOfTurnConfidenceThreshold: type: number description: >- The confidence threshold to use when determining if the end of a turn has been reached. Only used when `enableUniversalStreamingApi` is true. @default 0.7 minimum: 0 maximum: 1 example: 0.7 minEndOfTurnSilenceWhenConfident: type: number description: >- The minimum amount of silence in milliseconds required to detect end of turn when confident. Only used when `enableUniversalStreamingApi` is true. @default 160 minimum: 0 example: 160 wordFinalizationMaxWaitTime: type: number description: >- The maximum wait time for word finalization. Only used when `enableUniversalStreamingApi` is true. @default 160 minimum: 0 example: 160 maxTurnSilence: type: number description: >- The maximum amount of silence in milliseconds allowed in a turn before end of turn is triggered. Only used when `enableUniversalStreamingApi` is true. @default 400 minimum: 0 example: 400 realtimeUrl: type: string description: The WebSocket URL that the transcriber connects to. wordBoost: description: Add up to 2500 characters of custom vocabulary. type: array items: type: string maxLength: 2500 endUtteranceSilenceThreshold: type: number description: The duration of the end utterance silence threshold in milliseconds. disablePartialTranscripts: type: boolean description: >- Disable partial transcripts. Set to `true` to not receive partial transcripts. Defaults to `false`. fallbackPlan: description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. allOf: - $ref: '#/components/schemas/FallbackTranscriberPlan' required: - provider AzureSpeechTranscriber: type: object properties: provider: type: string description: This is the transcription provider that will be used. enum: - azure language: type: string description: >- This is the language that will be set for the transcription. The list of languages Azure supports can be found here: https://learn.microsoft.com/en-us/azure/ai-services/speech-service/language-support?tabs=stt enum: - af-ZA - am-ET - ar-AE - ar-BH - ar-DZ - ar-EG - ar-IL - ar-IQ - ar-JO - ar-KW - ar-LB - ar-LY - ar-MA - ar-OM - ar-PS - ar-QA - ar-SA - ar-SY - ar-TN - ar-YE - az-AZ - bg-BG - bn-IN - bs-BA - ca-ES - cs-CZ - cy-GB - da-DK - de-AT - de-CH - de-DE - el-GR - en-AU - en-CA - en-GB - en-GH - en-HK - en-IE - en-IN - en-KE - en-NG - en-NZ - en-PH - en-SG - en-TZ - en-US - en-ZA - es-AR - es-BO - es-CL - es-CO - es-CR - es-CU - es-DO - es-EC - es-ES - es-GQ - es-GT - es-HN - es-MX - es-NI - es-PA - es-PE - es-PR - es-PY - es-SV - es-US - es-UY - es-VE - et-EE - eu-ES - fa-IR - fi-FI - fil-PH - fr-BE - fr-CA - fr-CH - fr-FR - ga-IE - gl-ES - gu-IN - he-IL - hi-IN - hr-HR - hu-HU - hy-AM - id-ID - is-IS - it-CH - it-IT - ja-JP - jv-ID - ka-GE - kk-KZ - km-KH - kn-IN - ko-KR - lo-LA - lt-LT - lv-LV - mk-MK - ml-IN - mn-MN - mr-IN - ms-MY - mt-MT - my-MM - nb-NO - ne-NP - nl-BE - nl-NL - pa-IN - pl-PL - ps-AF - pt-BR - pt-PT - ro-RO - ru-RU - si-LK - sk-SK - sl-SI - so-SO - sq-AL - sr-RS - sv-SE - sw-KE - sw-TZ - ta-IN - te-IN - th-TH - tr-TR - uk-UA - ur-IN - uz-UZ - vi-VN - wuu-CN - yue-CN - zh-CN - zh-CN-shandong - zh-CN-sichuan - zh-HK - zh-TW - zu-ZA fallbackPlan: description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. allOf: - $ref: '#/components/schemas/FallbackTranscriberPlan' required: - provider CustomTranscriber: type: object properties: provider: type: string description: >- This is the transcription provider that will be used. Use `custom-transcriber` for providers that are not natively supported. enum: - custom-transcriber server: description: >- This is where the transcription request will be sent. Usage: 1. cozmox will initiate a websocket connection with `server.url`. 2. cozmox will send an initial text frame with the sample rate. Format: ``` { "type": "start", "encoding": "linear16", // 16-bit raw PCM format "container": "raw", "sampleRate": {{sampleRate}}, "channels": 2 // customer is channel 0, assistant is channel 1 } ``` 3. cozmox will send the audio data in 16-bit raw PCM format as binary frames. 4. You can read the messages something like this: ``` ws.on('message', (data, isBinary) => { if (isBinary) { pcmBuffer = Buffer.concat([pcmBuffer, data]); console.log(`Received PCM data, buffer size: ${pcmBuffer.length}`); } else { console.log('Received message:', JSON.parse(data.toString())); } }); ``` 5. You will respond with transcriptions as you have them. Format: ``` { "type": "transcriber-response", "transcription": "Hello, world!", "channel": "customer" | "assistant" } ``` allOf: - $ref: '#/components/schemas/Server' fallbackPlan: description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. allOf: - $ref: '#/components/schemas/FallbackTranscriberPlan' required: - provider - server DeepgramTranscriber: type: object properties: provider: type: string description: This is the transcription provider that will be used. enum: - deepgram model: description: >- This is the Deepgram model that will be used. A list of models can be found here: https://developers.deepgram.com/docs/models-languages-overview oneOf: - type: string enum: - nova-3 - nova-3-general - nova-3-medical - nova-2 - nova-2-general - nova-2-meeting - nova-2-phonecall - nova-2-finance - nova-2-conversationalai - nova-2-voicemail - nova-2-video - nova-2-medical - nova-2-drivethru - nova-2-automotive - nova - nova-general - nova-phonecall - nova-medical - enhanced - enhanced-general - enhanced-meeting - enhanced-phonecall - enhanced-finance - base - base-general - base-meeting - base-phonecall - base-finance - base-conversationalai - base-voicemail - base-video - whisper - type: string language: type: string description: >- This is the language that will be set for the transcription. The list of languages Deepgram supports can be found here: https://developers.deepgram.com/docs/models-languages-overview enum: - ar - az - ba - bg - br - ca - cs - da - da-DK - de - de-CH - el - en - en-AU - en-GB - en-IN - en-NZ - en-US - es - es-419 - es-LATAM - et - eu - fi - fr - fr-CA - ha - haw - he - hi - hi-Latn - hu - id - is - it - ja - jw - kn - ko - ko-KR - ln - lt - lv - mk - ms - multi - nl - nl-BE - 'no' - pl - pt - pt-BR - ro - ru - sk - sl - sn - so - sr - su - sv - sv-SE - ta - taq - th - th-TH - tr - tt - uk - ur - vi - yo - zh - zh-CN - zh-HK - zh-Hans - zh-Hant - zh-TW smartFormat: type: boolean description: >- This will be use smart format option provided by Deepgram. It's default disabled because it can sometimes format numbers as times but it's getting better. example: false mipOptOut: type: boolean description: >- If set to true, this will add mip_opt_out=true as a query parameter of all API requests. See https://developers.deepgram.com/docs/the-deepgram-model-improvement-partnership-program#want-to-opt-out This will only be used if you are using your own Deepgram API key. @default false example: false default: false numerals: type: boolean description: >- If set to true, this will cause deepgram to convert spoken numbers to literal numerals. For example, "my phone number is nine-seven-two..." would become "my phone number is 972..." @default false example: false confidenceThreshold: type: number description: |- Transcripts below this confidence threshold will be discarded. @default 0.4 minimum: 0 maximum: 1 example: 0.4 keywords: description: >- These keywords are passed to the transcription model to help it pick up use-case specific words. Anything that may not be a common word, like your company name, should be added here. type: array items: type: string pattern: /^\p{L}[\p{L}\d]*(?::[+-]?\d+)?$/u keyterm: description: >- Keyterm Prompting allows you improve Keyword Recall Rate (KRR) for important keyterms or phrases up to 90%. type: array items: type: string endpointing: type: number description: >- This is the timeout after which Deepgram will send transcription on user silence. You can read in-depth documentation here: https://developers.deepgram.com/docs/endpointing. Here are the most important bits: - Defaults to 10. This is recommended for most use cases to optimize for latency. - 10 can cause some missing transcriptions since because of the shorter context. This mostly happens for one-word utterances. For those uses cases, it's recommended to try 300. It will add a bit of latency but the quality and reliability of the experience will be better. - If neither 10 nor 300 work, contact support@cozmox.ai and we'll find another solution. @default 10 minimum: 10 maximum: 500 fallbackPlan: description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. allOf: - $ref: '#/components/schemas/FallbackTranscriberPlan' required: - provider ElevenLabsTranscriber: type: object properties: provider: type: string description: This is the transcription provider that will be used. enum: - 11labs model: type: string description: This is the model that will be used for the transcription. enum: - scribe_v1 language: type: string enum: - aa - ab - ae - af - ak - am - an - ar - as - av - ay - az - ba - be - bg - bh - bi - bm - bn - bo - br - bs - ca - ce - ch - co - cr - cs - cu - cv - cy - da - de - dv - dz - ee - el - en - eo - es - et - eu - fa - ff - fi - fj - fo - fr - fy - ga - gd - gl - gn - gu - gv - ha - he - hi - ho - hr - ht - hu - hy - hz - ia - id - ie - ig - ii - ik - io - is - it - iu - ja - jv - ka - kg - ki - kj - kk - kl - km - kn - ko - kr - ks - ku - kv - kw - ky - la - lb - lg - li - ln - lo - lt - lu - lv - mg - mh - mi - mk - ml - mn - mr - ms - mt - my - na - nb - nd - ne - ng - nl - nn - 'no' - nr - nv - ny - oc - oj - om - or - os - pa - pi - pl - ps - pt - qu - rm - rn - ro - ru - rw - sa - sc - sd - se - sg - si - sk - sl - sm - sn - so - sq - sr - ss - st - su - sv - sw - ta - te - tg - th - ti - tk - tl - tn - to - tr - ts - tt - tw - ty - ug - uk - ur - uz - ve - vi - vo - wa - wo - xh - yi - yue - yo - za - zh - zu fallbackPlan: description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. allOf: - $ref: '#/components/schemas/FallbackTranscriberPlan' required: - provider GladiaTranscriber: type: object properties: provider: type: string description: This is the transcription provider that will be used. enum: - gladia model: description: This is the Gladia model that will be used. Default is 'fast' oneOf: - enum: - fast - accurate - solaria-1 languageBehaviour: description: >- Defines how the transcription model detects the audio language. Default value is 'automatic single language'. oneOf: - type: string enum: - manual - automatic single language - automatic multiple languages language: type: string description: >- Defines the language to use for the transcription. Required when languageBehaviour is 'manual'. enum: - af - sq - am - ar - hy - as - az - ba - eu - be - bn - bs - br - bg - ca - zh - hr - cs - da - nl - en - et - fo - fi - fr - gl - ka - de - el - gu - ht - ha - haw - he - hi - hu - is - id - it - ja - jv - kn - kk - km - ko - lo - la - lv - ln - lt - lb - mk - mg - ms - ml - mt - mi - mr - mn - my - ne - 'no' - nn - oc - ps - fa - pl - pt - pa - ro - ru - sa - sr - sn - sd - si - sk - sl - so - es - su - sw - sv - tl - tg - ta - tt - te - th - bo - tr - tk - uk - ur - uz - vi - cy - yi - yo languages: type: string description: >- Defines the languages to use for the transcription. Required when languageBehaviour is 'manual'. enum: - af - sq - am - ar - hy - as - az - ba - eu - be - bn - bs - br - bg - ca - zh - hr - cs - da - nl - en - et - fo - fi - fr - gl - ka - de - el - gu - ht - ha - haw - he - hi - hu - is - id - it - ja - jv - kn - kk - km - ko - lo - la - lv - ln - lt - lb - mk - mg - ms - ml - mt - mi - mr - mn - my - ne - 'no' - nn - oc - ps - fa - pl - pt - pa - ro - ru - sa - sr - sn - sd - si - sk - sl - so - es - su - sw - sv - tl - tg - ta - tt - te - th - bo - tr - tk - uk - ur - uz - vi - cy - yi - yo transcriptionHint: type: string description: >- Provides a custom vocabulary to the model to improve accuracy of transcribing context specific words, technical terms, names, etc. If empty, this argument is ignored. ⚠️ Warning ⚠️: Please be aware that the transcription_hint field has a character limit of 600. If you provide a transcription_hint longer than 600 characters, it will be automatically truncated to meet this limit. maxLength: 600 example: custom vocabulary prosody: type: boolean description: >- If prosody is true, you will get a transcription that can contain prosodies i.e. (laugh) (giggles) (malefic laugh) (toss) (music)… Default value is false. example: false audioEnhancer: type: boolean description: >- If true, audio will be pre-processed to improve accuracy but latency will increase. Default value is false. example: false confidenceThreshold: type: number description: |- Transcripts below this confidence threshold will be discarded. @default 0.4 minimum: 0 maximum: 1 example: 0.4 fallbackPlan: description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. allOf: - $ref: '#/components/schemas/FallbackTranscriberPlan' required: - provider GoogleTranscriber: type: object properties: provider: type: string description: This is the transcription provider that will be used. enum: - google model: type: string description: This is the model that will be used for the transcription. enum: - gemini-2.5-pro - gemini-2.5-flash - gemini-2.5-flash-lite - gemini-2.5-pro-preview-05-06 - gemini-2.5-flash-preview-05-20 - gemini-2.5-flash-preview-04-17 - gemini-2.0-flash-thinking-exp - gemini-2.0-pro-exp-02-05 - gemini-2.0-flash - gemini-2.0-flash-lite - gemini-2.0-flash-lite-preview-02-05 - gemini-2.0-flash-exp - gemini-2.0-flash-realtime-exp - gemini-1.5-flash - gemini-1.5-flash-002 - gemini-1.5-pro - gemini-1.5-pro-002 - gemini-1.0-pro language: type: string description: This is the language that will be set for the transcription. enum: - Multilingual - Arabic - Bengali - Bulgarian - Chinese - Croatian - Czech - Danish - Dutch - English - Estonian - Finnish - French - German - Greek - Hebrew - Hindi - Hungarian - Indonesian - Italian - Japanese - Korean - Latvian - Lithuanian - Norwegian - Polish - Portuguese - Romanian - Russian - Serbian - Slovak - Slovenian - Spanish - Swahili - Swedish - Thai - Turkish - Ukrainian - Vietnamese fallbackPlan: description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. allOf: - $ref: '#/components/schemas/FallbackTranscriberPlan' required: - provider SpeechmaticsTranscriber: type: object properties: provider: type: string description: This is the transcription provider that will be used. enum: - speechmatics model: type: string description: This is the model that will be used for the transcription. enum: - default language: type: string enum: - auto - ar - ba - eu - be - bn - bg - yue - ca - hr - cs - da - nl - en - eo - et - fi - fr - gl - de - el - he - hi - hu - id - ia - ga - it - ja - ko - lv - lt - ms - mt - cmn - mr - mn - 'no' - fa - pl - pt - ro - ru - sk - sl - es - sw - sv - ta - th - tr - uk - ur - ug - vi - cy fallbackPlan: description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. allOf: - $ref: '#/components/schemas/FallbackTranscriberPlan' required: - provider TalkscriberTranscriber: type: object properties: provider: type: string description: This is the transcription provider that will be used. enum: - talkscriber model: type: string description: This is the model that will be used for the transcription. enum: - whisper language: type: string description: >- This is the language that will be set for the transcription. The list of languages Whisper supports can be found here: https://github.com/openai/whisper/blob/main/whisper/tokenizer.py enum: - en - zh - de - es - ru - ko - fr - ja - pt - tr - pl - ca - nl - ar - sv - it - id - hi - fi - vi - he - uk - el - ms - cs - ro - da - hu - ta - 'no' - th - ur - hr - bg - lt - la - mi - ml - cy - sk - te - fa - lv - bn - sr - az - sl - kn - et - mk - br - eu - is - hy - ne - mn - bs - kk - sq - sw - gl - mr - pa - si - km - sn - yo - so - af - oc - ka - be - tg - sd - gu - am - yi - lo - uz - fo - ht - ps - tk - nn - mt - sa - lb - my - bo - tl - mg - as - tt - haw - ln - ha - ba - jw - su - yue fallbackPlan: description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. allOf: - $ref: '#/components/schemas/FallbackTranscriberPlan' required: - provider OpenAITranscriber: type: object properties: provider: type: string description: This is the transcription provider that will be used. enum: - openai model: type: string description: This is the model that will be used for the transcription. enum: - gpt-4o-transcribe - gpt-4o-mini-transcribe language: type: string description: This is the language that will be set for the transcription. enum: - af - ar - hy - az - be - bs - bg - ca - zh - hr - cs - da - nl - en - et - fi - fr - gl - de - el - he - hi - hu - is - id - it - ja - kn - kk - ko - lv - lt - mk - ms - mr - mi - ne - 'no' - fa - pl - pt - ro - ru - sr - sk - sl - es - sw - sv - tl - ta - th - tr - uk - ur - vi - cy fallbackPlan: description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. allOf: - $ref: '#/components/schemas/FallbackTranscriberPlan' required: - provider - model CartesiaTranscriber: type: object properties: provider: type: string enum: - cartesia model: type: string enum: - ink-whisper language: type: string enum: - aa - ab - ae - af - ak - am - an - ar - as - av - ay - az - ba - be - bg - bh - bi - bm - bn - bo - br - bs - ca - ce - ch - co - cr - cs - cu - cv - cy - da - de - dv - dz - ee - el - en - eo - es - et - eu - fa - ff - fi - fj - fo - fr - fy - ga - gd - gl - gn - gu - gv - ha - he - hi - ho - hr - ht - hu - hy - hz - ia - id - ie - ig - ii - ik - io - is - it - iu - ja - jv - ka - kg - ki - kj - kk - kl - km - kn - ko - kr - ks - ku - kv - kw - ky - la - lb - lg - li - ln - lo - lt - lu - lv - mg - mh - mi - mk - ml - mn - mr - ms - mt - my - na - nb - nd - ne - ng - nl - nn - 'no' - nr - nv - ny - oc - oj - om - or - os - pa - pi - pl - ps - pt - qu - rm - rn - ro - ru - rw - sa - sc - sd - se - sg - si - sk - sl - sm - sn - so - sq - sr - ss - st - su - sv - sw - ta - te - tg - th - ti - tk - tl - tn - to - tr - ts - tt - tw - ty - ug - uk - ur - uz - ve - vi - vo - wa - wo - xh - yi - yue - yo - za - zh - zu fallbackPlan: description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. allOf: - $ref: '#/components/schemas/FallbackTranscriberPlan' required: - provider AnthropicModel: type: object properties: messages: description: This is the starting state for the conversation. type: array items: $ref: '#/components/schemas/OpenAIMessage' tools: type: array description: >- These are the tools that the assistant can use during the call. To use existing tools, use `toolIds`. Both `tools` and `toolIds` can be used together. items: oneOf: - $ref: '#/components/schemas/CreateApiRequestToolDTO' title: ApiRequestTool - $ref: '#/components/schemas/CreateBashToolDTO' title: BashTool - $ref: '#/components/schemas/CreateComputerToolDTO' title: ComputerTool - $ref: '#/components/schemas/CreateDtmfToolDTO' title: DtmfTool - $ref: '#/components/schemas/CreateEndCallToolDTO' title: EndCallTool - $ref: '#/components/schemas/CreateFunctionToolDTO' title: FunctionTool - $ref: >- #/components/schemas/CreateGoHighLevelCalendarAvailabilityToolDTO title: GoHighLevelCalendarAvailabilityTool - $ref: >- #/components/schemas/CreateGoHighLevelCalendarEventCreateToolDTO title: GoHighLevelCalendarEventCreateTool - $ref: '#/components/schemas/CreateGoHighLevelContactCreateToolDTO' title: GoHighLevelContactCreateTool - $ref: '#/components/schemas/CreateGoHighLevelContactGetToolDTO' title: GoHighLevelContactGetTool - $ref: >- #/components/schemas/CreateGoogleCalendarCheckAvailabilityToolDTO title: GoogleCalendarCheckAvailabilityTool - $ref: '#/components/schemas/CreateGoogleCalendarCreateEventToolDTO' title: GoogleCalendarCreateEventTool - $ref: '#/components/schemas/CreateGoogleSheetsRowAppendToolDTO' title: GoogleSheetsRowAppendTool - $ref: '#/components/schemas/CreateMcpToolDTO' title: McpTool - $ref: '#/components/schemas/CreateQueryToolDTO' title: QueryTool - $ref: '#/components/schemas/CreateSlackSendMessageToolDTO' title: SlackSendMessageTool - $ref: '#/components/schemas/CreateSmsToolDTO' title: SmsTool - $ref: '#/components/schemas/CreateTextEditorToolDTO' title: TextEditorTool - $ref: '#/components/schemas/CreateTransferCallToolDTO' title: TransferCallTool toolIds: description: >- These are the tools that the assistant can use during the call. To use transient tools, use `tools`. Both `tools` and `toolIds` can be used together. type: array items: type: string knowledgeBase: description: These are the options for the knowledge base. oneOf: - $ref: '#/components/schemas/CreateCustomKnowledgeBaseDTO' title: Custom knowledgeBaseId: type: string description: This is the ID of the knowledge base the model will use. model: type: string description: The specific Anthropic/Claude model that will be used. enum: - claude-3-opus-20240229 - claude-3-sonnet-20240229 - claude-3-haiku-20240307 - claude-3-5-sonnet-20240620 - claude-3-5-sonnet-20241022 - claude-3-5-haiku-20241022 - claude-3-7-sonnet-20250219 - claude-opus-4-20250514 - claude-sonnet-4-20250514 provider: type: string description: The provider identifier for Anthropic. enum: - anthropic thinking: description: |- Optional configuration for Anthropic's thinking feature. Only applicable for claude-3-7-sonnet-20250219 model. If provided, maxTokens must be greater than thinking.budgetTokens. allOf: - $ref: '#/components/schemas/AnthropicThinkingConfig' temperature: type: number description: >- This is the temperature that will be used for calls. Default is 0 to leverage caching for lower latency. minimum: 0 maximum: 2 maxTokens: type: number description: >- This is the max number of tokens that the assistant will be allowed to generate in each turn of the conversation. Default is 250. minimum: 50 maximum: 10000 emotionRecognitionEnabled: type: boolean description: >- This determines whether we detect user's emotion while they speak and send it as an additional info to model. Default `false` because the model is usually are good at understanding the user's emotion from text. @default false numFastTurns: type: number description: >- This sets how many turns at the start of the conversation to use a smaller, faster model from the same provider before switching to the primary model. Example, gpt-3.5-turbo if provider is openai. Default is 0. @default 0 minimum: 0 required: - model - provider AnyscaleModel: type: object properties: messages: description: This is the starting state for the conversation. type: array items: $ref: '#/components/schemas/OpenAIMessage' tools: type: array description: >- These are the tools that the assistant can use during the call. To use existing tools, use `toolIds`. Both `tools` and `toolIds` can be used together. items: oneOf: - $ref: '#/components/schemas/CreateApiRequestToolDTO' title: ApiRequestTool - $ref: '#/components/schemas/CreateBashToolDTO' title: BashTool - $ref: '#/components/schemas/CreateComputerToolDTO' title: ComputerTool - $ref: '#/components/schemas/CreateDtmfToolDTO' title: DtmfTool - $ref: '#/components/schemas/CreateEndCallToolDTO' title: EndCallTool - $ref: '#/components/schemas/CreateFunctionToolDTO' title: FunctionTool - $ref: >- #/components/schemas/CreateGoHighLevelCalendarAvailabilityToolDTO title: GoHighLevelCalendarAvailabilityTool - $ref: >- #/components/schemas/CreateGoHighLevelCalendarEventCreateToolDTO title: GoHighLevelCalendarEventCreateTool - $ref: '#/components/schemas/CreateGoHighLevelContactCreateToolDTO' title: GoHighLevelContactCreateTool - $ref: '#/components/schemas/CreateGoHighLevelContactGetToolDTO' title: GoHighLevelContactGetTool - $ref: >- #/components/schemas/CreateGoogleCalendarCheckAvailabilityToolDTO title: GoogleCalendarCheckAvailabilityTool - $ref: '#/components/schemas/CreateGoogleCalendarCreateEventToolDTO' title: GoogleCalendarCreateEventTool - $ref: '#/components/schemas/CreateGoogleSheetsRowAppendToolDTO' title: GoogleSheetsRowAppendTool - $ref: '#/components/schemas/CreateMcpToolDTO' title: McpTool - $ref: '#/components/schemas/CreateQueryToolDTO' title: QueryTool - $ref: '#/components/schemas/CreateSlackSendMessageToolDTO' title: SlackSendMessageTool - $ref: '#/components/schemas/CreateSmsToolDTO' title: SmsTool - $ref: '#/components/schemas/CreateTextEditorToolDTO' title: TextEditorTool - $ref: '#/components/schemas/CreateTransferCallToolDTO' title: TransferCallTool toolIds: description: >- These are the tools that the assistant can use during the call. To use transient tools, use `tools`. Both `tools` and `toolIds` can be used together. type: array items: type: string knowledgeBase: description: These are the options for the knowledge base. oneOf: - $ref: '#/components/schemas/CreateCustomKnowledgeBaseDTO' title: Custom knowledgeBaseId: type: string description: This is the ID of the knowledge base the model will use. provider: type: string enum: - anyscale model: type: string description: >- This is the name of the model. Ex. cognitivecomputations/dolphin-mixtral-8x7b temperature: type: number description: >- This is the temperature that will be used for calls. Default is 0 to leverage caching for lower latency. minimum: 0 maximum: 2 maxTokens: type: number description: >- This is the max number of tokens that the assistant will be allowed to generate in each turn of the conversation. Default is 250. minimum: 50 maximum: 10000 emotionRecognitionEnabled: type: boolean description: >- This determines whether we detect user's emotion while they speak and send it as an additional info to model. Default `false` because the model is usually are good at understanding the user's emotion from text. @default false numFastTurns: type: number description: >- This sets how many turns at the start of the conversation to use a smaller, faster model from the same provider before switching to the primary model. Example, gpt-3.5-turbo if provider is openai. Default is 0. @default 0 minimum: 0 required: - provider - model CerebrasModel: type: object properties: messages: description: This is the starting state for the conversation. type: array items: $ref: '#/components/schemas/OpenAIMessage' tools: type: array description: >- These are the tools that the assistant can use during the call. To use existing tools, use `toolIds`. Both `tools` and `toolIds` can be used together. items: oneOf: - $ref: '#/components/schemas/CreateApiRequestToolDTO' title: ApiRequestTool - $ref: '#/components/schemas/CreateBashToolDTO' title: BashTool - $ref: '#/components/schemas/CreateComputerToolDTO' title: ComputerTool - $ref: '#/components/schemas/CreateDtmfToolDTO' title: DtmfTool - $ref: '#/components/schemas/CreateEndCallToolDTO' title: EndCallTool - $ref: '#/components/schemas/CreateFunctionToolDTO' title: FunctionTool - $ref: >- #/components/schemas/CreateGoHighLevelCalendarAvailabilityToolDTO title: GoHighLevelCalendarAvailabilityTool - $ref: >- #/components/schemas/CreateGoHighLevelCalendarEventCreateToolDTO title: GoHighLevelCalendarEventCreateTool - $ref: '#/components/schemas/CreateGoHighLevelContactCreateToolDTO' title: GoHighLevelContactCreateTool - $ref: '#/components/schemas/CreateGoHighLevelContactGetToolDTO' title: GoHighLevelContactGetTool - $ref: >- #/components/schemas/CreateGoogleCalendarCheckAvailabilityToolDTO title: GoogleCalendarCheckAvailabilityTool - $ref: '#/components/schemas/CreateGoogleCalendarCreateEventToolDTO' title: GoogleCalendarCreateEventTool - $ref: '#/components/schemas/CreateGoogleSheetsRowAppendToolDTO' title: GoogleSheetsRowAppendTool - $ref: '#/components/schemas/CreateMcpToolDTO' title: McpTool - $ref: '#/components/schemas/CreateQueryToolDTO' title: QueryTool - $ref: '#/components/schemas/CreateSlackSendMessageToolDTO' title: SlackSendMessageTool - $ref: '#/components/schemas/CreateSmsToolDTO' title: SmsTool - $ref: '#/components/schemas/CreateTextEditorToolDTO' title: TextEditorTool - $ref: '#/components/schemas/CreateTransferCallToolDTO' title: TransferCallTool toolIds: description: >- These are the tools that the assistant can use during the call. To use transient tools, use `tools`. Both `tools` and `toolIds` can be used together. type: array items: type: string knowledgeBase: description: These are the options for the knowledge base. oneOf: - $ref: '#/components/schemas/CreateCustomKnowledgeBaseDTO' title: Custom knowledgeBaseId: type: string description: This is the ID of the knowledge base the model will use. model: type: string description: >- This is the name of the model. Ex. cognitivecomputations/dolphin-mixtral-8x7b enum: - llama3.1-8b - llama-3.3-70b provider: type: string enum: - cerebras temperature: type: number description: >- This is the temperature that will be used for calls. Default is 0 to leverage caching for lower latency. minimum: 0 maximum: 2 maxTokens: type: number description: >- This is the max number of tokens that the assistant will be allowed to generate in each turn of the conversation. Default is 250. minimum: 50 maximum: 10000 emotionRecognitionEnabled: type: boolean description: >- This determines whether we detect user's emotion while they speak and send it as an additional info to model. Default `false` because the model is usually are good at understanding the user's emotion from text. @default false numFastTurns: type: number description: >- This sets how many turns at the start of the conversation to use a smaller, faster model from the same provider before switching to the primary model. Example, gpt-3.5-turbo if provider is openai. Default is 0. @default 0 minimum: 0 required: - model - provider CustomLLMModel: type: object properties: messages: description: This is the starting state for the conversation. type: array items: $ref: '#/components/schemas/OpenAIMessage' tools: type: array description: >- These are the tools that the assistant can use during the call. To use existing tools, use `toolIds`. Both `tools` and `toolIds` can be used together. items: oneOf: - $ref: '#/components/schemas/CreateApiRequestToolDTO' title: ApiRequestTool - $ref: '#/components/schemas/CreateBashToolDTO' title: BashTool - $ref: '#/components/schemas/CreateComputerToolDTO' title: ComputerTool - $ref: '#/components/schemas/CreateDtmfToolDTO' title: DtmfTool - $ref: '#/components/schemas/CreateEndCallToolDTO' title: EndCallTool - $ref: '#/components/schemas/CreateFunctionToolDTO' title: FunctionTool - $ref: >- #/components/schemas/CreateGoHighLevelCalendarAvailabilityToolDTO title: GoHighLevelCalendarAvailabilityTool - $ref: >- #/components/schemas/CreateGoHighLevelCalendarEventCreateToolDTO title: GoHighLevelCalendarEventCreateTool - $ref: '#/components/schemas/CreateGoHighLevelContactCreateToolDTO' title: GoHighLevelContactCreateTool - $ref: '#/components/schemas/CreateGoHighLevelContactGetToolDTO' title: GoHighLevelContactGetTool - $ref: >- #/components/schemas/CreateGoogleCalendarCheckAvailabilityToolDTO title: GoogleCalendarCheckAvailabilityTool - $ref: '#/components/schemas/CreateGoogleCalendarCreateEventToolDTO' title: GoogleCalendarCreateEventTool - $ref: '#/components/schemas/CreateGoogleSheetsRowAppendToolDTO' title: GoogleSheetsRowAppendTool - $ref: '#/components/schemas/CreateMcpToolDTO' title: McpTool - $ref: '#/components/schemas/CreateQueryToolDTO' title: QueryTool - $ref: '#/components/schemas/CreateSlackSendMessageToolDTO' title: SlackSendMessageTool - $ref: '#/components/schemas/CreateSmsToolDTO' title: SmsTool - $ref: '#/components/schemas/CreateTextEditorToolDTO' title: TextEditorTool - $ref: '#/components/schemas/CreateTransferCallToolDTO' title: TransferCallTool toolIds: description: >- These are the tools that the assistant can use during the call. To use transient tools, use `tools`. Both `tools` and `toolIds` can be used together. type: array items: type: string knowledgeBase: description: These are the options for the knowledge base. oneOf: - $ref: '#/components/schemas/CreateCustomKnowledgeBaseDTO' title: Custom knowledgeBaseId: type: string description: This is the ID of the knowledge base the model will use. provider: type: string description: >- This is the provider that will be used for the model. Any service, including your own server, that is compatible with the OpenAI API can be used. enum: - custom-llm metadataSendMode: type: string description: >- This determines whether metadata is sent in requests to the custom provider. - `off` will not send any metadata. payload will look like `{ messages }` - `variable` will send `assistant.metadata` as a variable on the payload. payload will look like `{ messages, metadata }` - `destructured` will send `assistant.metadata` fields directly on the payload. payload will look like `{ messages, ...metadata }` Further, `variable` and `destructured` will send `call`, `phoneNumber`, and `customer` objects in the payload. Default is `variable`. enum: - 'off' - variable - destructured url: type: string description: >- These is the URL we'll use for the OpenAI client's `baseURL`. Ex. https://openrouter.ai/api/v1 timeoutSeconds: type: number description: >- This sets the timeout for the connection to the custom provider without needing to stream any tokens back. Default is 20 seconds. minimum: 20 maximum: 600 model: type: string description: >- This is the name of the model. Ex. cognitivecomputations/dolphin-mixtral-8x7b temperature: type: number description: >- This is the temperature that will be used for calls. Default is 0 to leverage caching for lower latency. minimum: 0 maximum: 2 maxTokens: type: number description: >- This is the max number of tokens that the assistant will be allowed to generate in each turn of the conversation. Default is 250. minimum: 50 maximum: 10000 emotionRecognitionEnabled: type: boolean description: >- This determines whether we detect user's emotion while they speak and send it as an additional info to model. Default `false` because the model is usually are good at understanding the user's emotion from text. @default false numFastTurns: type: number description: >- This sets how many turns at the start of the conversation to use a smaller, faster model from the same provider before switching to the primary model. Example, gpt-3.5-turbo if provider is openai. Default is 0. @default 0 minimum: 0 required: - provider - url - model DeepInfraModel: type: object properties: messages: description: This is the starting state for the conversation. type: array items: $ref: '#/components/schemas/OpenAIMessage' tools: type: array description: >- These are the tools that the assistant can use during the call. To use existing tools, use `toolIds`. Both `tools` and `toolIds` can be used together. items: oneOf: - $ref: '#/components/schemas/CreateApiRequestToolDTO' title: ApiRequestTool - $ref: '#/components/schemas/CreateBashToolDTO' title: BashTool - $ref: '#/components/schemas/CreateComputerToolDTO' title: ComputerTool - $ref: '#/components/schemas/CreateDtmfToolDTO' title: DtmfTool - $ref: '#/components/schemas/CreateEndCallToolDTO' title: EndCallTool - $ref: '#/components/schemas/CreateFunctionToolDTO' title: FunctionTool - $ref: >- #/components/schemas/CreateGoHighLevelCalendarAvailabilityToolDTO title: GoHighLevelCalendarAvailabilityTool - $ref: >- #/components/schemas/CreateGoHighLevelCalendarEventCreateToolDTO title: GoHighLevelCalendarEventCreateTool - $ref: '#/components/schemas/CreateGoHighLevelContactCreateToolDTO' title: GoHighLevelContactCreateTool - $ref: '#/components/schemas/CreateGoHighLevelContactGetToolDTO' title: GoHighLevelContactGetTool - $ref: >- #/components/schemas/CreateGoogleCalendarCheckAvailabilityToolDTO title: GoogleCalendarCheckAvailabilityTool - $ref: '#/components/schemas/CreateGoogleCalendarCreateEventToolDTO' title: GoogleCalendarCreateEventTool - $ref: '#/components/schemas/CreateGoogleSheetsRowAppendToolDTO' title: GoogleSheetsRowAppendTool - $ref: '#/components/schemas/CreateMcpToolDTO' title: McpTool - $ref: '#/components/schemas/CreateQueryToolDTO' title: QueryTool - $ref: '#/components/schemas/CreateSlackSendMessageToolDTO' title: SlackSendMessageTool - $ref: '#/components/schemas/CreateSmsToolDTO' title: SmsTool - $ref: '#/components/schemas/CreateTextEditorToolDTO' title: TextEditorTool - $ref: '#/components/schemas/CreateTransferCallToolDTO' title: TransferCallTool toolIds: description: >- These are the tools that the assistant can use during the call. To use transient tools, use `tools`. Both `tools` and `toolIds` can be used together. type: array items: type: string knowledgeBase: description: These are the options for the knowledge base. oneOf: - $ref: '#/components/schemas/CreateCustomKnowledgeBaseDTO' title: Custom knowledgeBaseId: type: string description: This is the ID of the knowledge base the model will use. provider: type: string enum: - deepinfra model: type: string description: >- This is the name of the model. Ex. cognitivecomputations/dolphin-mixtral-8x7b temperature: type: number description: >- This is the temperature that will be used for calls. Default is 0 to leverage caching for lower latency. minimum: 0 maximum: 2 maxTokens: type: number description: >- This is the max number of tokens that the assistant will be allowed to generate in each turn of the conversation. Default is 250. minimum: 50 maximum: 10000 emotionRecognitionEnabled: type: boolean description: >- This determines whether we detect user's emotion while they speak and send it as an additional info to model. Default `false` because the model is usually are good at understanding the user's emotion from text. @default false numFastTurns: type: number description: >- This sets how many turns at the start of the conversation to use a smaller, faster model from the same provider before switching to the primary model. Example, gpt-3.5-turbo if provider is openai. Default is 0. @default 0 minimum: 0 required: - provider - model DeepSeekModel: type: object properties: messages: description: This is the starting state for the conversation. type: array items: $ref: '#/components/schemas/OpenAIMessage' tools: type: array description: >- These are the tools that the assistant can use during the call. To use existing tools, use `toolIds`. Both `tools` and `toolIds` can be used together. items: oneOf: - $ref: '#/components/schemas/CreateApiRequestToolDTO' title: ApiRequestTool - $ref: '#/components/schemas/CreateBashToolDTO' title: BashTool - $ref: '#/components/schemas/CreateComputerToolDTO' title: ComputerTool - $ref: '#/components/schemas/CreateDtmfToolDTO' title: DtmfTool - $ref: '#/components/schemas/CreateEndCallToolDTO' title: EndCallTool - $ref: '#/components/schemas/CreateFunctionToolDTO' title: FunctionTool - $ref: >- #/components/schemas/CreateGoHighLevelCalendarAvailabilityToolDTO title: GoHighLevelCalendarAvailabilityTool - $ref: >- #/components/schemas/CreateGoHighLevelCalendarEventCreateToolDTO title: GoHighLevelCalendarEventCreateTool - $ref: '#/components/schemas/CreateGoHighLevelContactCreateToolDTO' title: GoHighLevelContactCreateTool - $ref: '#/components/schemas/CreateGoHighLevelContactGetToolDTO' title: GoHighLevelContactGetTool - $ref: >- #/components/schemas/CreateGoogleCalendarCheckAvailabilityToolDTO title: GoogleCalendarCheckAvailabilityTool - $ref: '#/components/schemas/CreateGoogleCalendarCreateEventToolDTO' title: GoogleCalendarCreateEventTool - $ref: '#/components/schemas/CreateGoogleSheetsRowAppendToolDTO' title: GoogleSheetsRowAppendTool - $ref: '#/components/schemas/CreateMcpToolDTO' title: McpTool - $ref: '#/components/schemas/CreateQueryToolDTO' title: QueryTool - $ref: '#/components/schemas/CreateSlackSendMessageToolDTO' title: SlackSendMessageTool - $ref: '#/components/schemas/CreateSmsToolDTO' title: SmsTool - $ref: '#/components/schemas/CreateTextEditorToolDTO' title: TextEditorTool - $ref: '#/components/schemas/CreateTransferCallToolDTO' title: TransferCallTool toolIds: description: >- These are the tools that the assistant can use during the call. To use transient tools, use `tools`. Both `tools` and `toolIds` can be used together. type: array items: type: string knowledgeBase: description: These are the options for the knowledge base. oneOf: - $ref: '#/components/schemas/CreateCustomKnowledgeBaseDTO' title: Custom knowledgeBaseId: type: string description: This is the ID of the knowledge base the model will use. model: type: string description: >- This is the name of the model. Ex. cognitivecomputations/dolphin-mixtral-8x7b enum: - deepseek-chat - deepseek-reasoner provider: type: string enum: - deep-seek temperature: type: number description: >- This is the temperature that will be used for calls. Default is 0 to leverage caching for lower latency. minimum: 0 maximum: 2 maxTokens: type: number description: >- This is the max number of tokens that the assistant will be allowed to generate in each turn of the conversation. Default is 250. minimum: 50 maximum: 10000 emotionRecognitionEnabled: type: boolean description: >- This determines whether we detect user's emotion while they speak and send it as an additional info to model. Default `false` because the model is usually are good at understanding the user's emotion from text. @default false numFastTurns: type: number description: >- This sets how many turns at the start of the conversation to use a smaller, faster model from the same provider before switching to the primary model. Example, gpt-3.5-turbo if provider is openai. Default is 0. @default 0 minimum: 0 required: - model - provider GoogleModel: type: object properties: messages: description: This is the starting state for the conversation. type: array items: $ref: '#/components/schemas/OpenAIMessage' tools: type: array description: >- These are the tools that the assistant can use during the call. To use existing tools, use `toolIds`. Both `tools` and `toolIds` can be used together. items: oneOf: - $ref: '#/components/schemas/CreateApiRequestToolDTO' title: ApiRequestTool - $ref: '#/components/schemas/CreateBashToolDTO' title: BashTool - $ref: '#/components/schemas/CreateComputerToolDTO' title: ComputerTool - $ref: '#/components/schemas/CreateDtmfToolDTO' title: DtmfTool - $ref: '#/components/schemas/CreateEndCallToolDTO' title: EndCallTool - $ref: '#/components/schemas/CreateFunctionToolDTO' title: FunctionTool - $ref: >- #/components/schemas/CreateGoHighLevelCalendarAvailabilityToolDTO title: GoHighLevelCalendarAvailabilityTool - $ref: >- #/components/schemas/CreateGoHighLevelCalendarEventCreateToolDTO title: GoHighLevelCalendarEventCreateTool - $ref: '#/components/schemas/CreateGoHighLevelContactCreateToolDTO' title: GoHighLevelContactCreateTool - $ref: '#/components/schemas/CreateGoHighLevelContactGetToolDTO' title: GoHighLevelContactGetTool - $ref: >- #/components/schemas/CreateGoogleCalendarCheckAvailabilityToolDTO title: GoogleCalendarCheckAvailabilityTool - $ref: '#/components/schemas/CreateGoogleCalendarCreateEventToolDTO' title: GoogleCalendarCreateEventTool - $ref: '#/components/schemas/CreateGoogleSheetsRowAppendToolDTO' title: GoogleSheetsRowAppendTool - $ref: '#/components/schemas/CreateMcpToolDTO' title: McpTool - $ref: '#/components/schemas/CreateQueryToolDTO' title: QueryTool - $ref: '#/components/schemas/CreateSlackSendMessageToolDTO' title: SlackSendMessageTool - $ref: '#/components/schemas/CreateSmsToolDTO' title: SmsTool - $ref: '#/components/schemas/CreateTextEditorToolDTO' title: TextEditorTool - $ref: '#/components/schemas/CreateTransferCallToolDTO' title: TransferCallTool toolIds: description: >- These are the tools that the assistant can use during the call. To use transient tools, use `tools`. Both `tools` and `toolIds` can be used together. type: array items: type: string knowledgeBase: description: These are the options for the knowledge base. oneOf: - $ref: '#/components/schemas/CreateCustomKnowledgeBaseDTO' title: Custom knowledgeBaseId: type: string description: This is the ID of the knowledge base the model will use. model: type: string description: This is the Google model that will be used. enum: - gemini-2.5-pro - gemini-2.5-flash - gemini-2.5-flash-lite - gemini-2.5-pro-preview-05-06 - gemini-2.5-flash-preview-05-20 - gemini-2.5-flash-preview-04-17 - gemini-2.0-flash-thinking-exp - gemini-2.0-pro-exp-02-05 - gemini-2.0-flash - gemini-2.0-flash-lite - gemini-2.0-flash-lite-preview-02-05 - gemini-2.0-flash-exp - gemini-2.0-flash-realtime-exp - gemini-1.5-flash - gemini-1.5-flash-002 - gemini-1.5-pro - gemini-1.5-pro-002 - gemini-1.0-pro provider: type: string enum: - google realtimeConfig: description: >- This is the session configuration for the Gemini Flash 2.0 Multimodal Live API. Only applicable if the model `gemini-2.0-flash-realtime-exp` is selected. allOf: - $ref: '#/components/schemas/GoogleRealtimeConfig' temperature: type: number description: >- This is the temperature that will be used for calls. Default is 0 to leverage caching for lower latency. minimum: 0 maximum: 2 maxTokens: type: number description: >- This is the max number of tokens that the assistant will be allowed to generate in each turn of the conversation. Default is 250. minimum: 50 maximum: 10000 emotionRecognitionEnabled: type: boolean description: >- This determines whether we detect user's emotion while they speak and send it as an additional info to model. Default `false` because the model is usually are good at understanding the user's emotion from text. @default false numFastTurns: type: number description: >- This sets how many turns at the start of the conversation to use a smaller, faster model from the same provider before switching to the primary model. Example, gpt-3.5-turbo if provider is openai. Default is 0. @default 0 minimum: 0 required: - model - provider GroqModel: type: object properties: messages: description: This is the starting state for the conversation. type: array items: $ref: '#/components/schemas/OpenAIMessage' tools: type: array description: >- These are the tools that the assistant can use during the call. To use existing tools, use `toolIds`. Both `tools` and `toolIds` can be used together. items: oneOf: - $ref: '#/components/schemas/CreateApiRequestToolDTO' title: ApiRequestTool - $ref: '#/components/schemas/CreateBashToolDTO' title: BashTool - $ref: '#/components/schemas/CreateComputerToolDTO' title: ComputerTool - $ref: '#/components/schemas/CreateDtmfToolDTO' title: DtmfTool - $ref: '#/components/schemas/CreateEndCallToolDTO' title: EndCallTool - $ref: '#/components/schemas/CreateFunctionToolDTO' title: FunctionTool - $ref: >- #/components/schemas/CreateGoHighLevelCalendarAvailabilityToolDTO title: GoHighLevelCalendarAvailabilityTool - $ref: >- #/components/schemas/CreateGoHighLevelCalendarEventCreateToolDTO title: GoHighLevelCalendarEventCreateTool - $ref: '#/components/schemas/CreateGoHighLevelContactCreateToolDTO' title: GoHighLevelContactCreateTool - $ref: '#/components/schemas/CreateGoHighLevelContactGetToolDTO' title: GoHighLevelContactGetTool - $ref: >- #/components/schemas/CreateGoogleCalendarCheckAvailabilityToolDTO title: GoogleCalendarCheckAvailabilityTool - $ref: '#/components/schemas/CreateGoogleCalendarCreateEventToolDTO' title: GoogleCalendarCreateEventTool - $ref: '#/components/schemas/CreateGoogleSheetsRowAppendToolDTO' title: GoogleSheetsRowAppendTool - $ref: '#/components/schemas/CreateMcpToolDTO' title: McpTool - $ref: '#/components/schemas/CreateQueryToolDTO' title: QueryTool - $ref: '#/components/schemas/CreateSlackSendMessageToolDTO' title: SlackSendMessageTool - $ref: '#/components/schemas/CreateSmsToolDTO' title: SmsTool - $ref: '#/components/schemas/CreateTextEditorToolDTO' title: TextEditorTool - $ref: '#/components/schemas/CreateTransferCallToolDTO' title: TransferCallTool toolIds: description: >- These are the tools that the assistant can use during the call. To use transient tools, use `tools`. Both `tools` and `toolIds` can be used together. type: array items: type: string knowledgeBase: description: These are the options for the knowledge base. oneOf: - $ref: '#/components/schemas/CreateCustomKnowledgeBaseDTO' title: Custom knowledgeBaseId: type: string description: This is the ID of the knowledge base the model will use. model: type: string description: >- This is the name of the model. Ex. cognitivecomputations/dolphin-mixtral-8x7b enum: - deepseek-r1-distill-llama-70b - llama-3.3-70b-versatile - llama-3.1-405b-reasoning - llama-3.1-8b-instant - llama3-8b-8192 - llama3-70b-8192 - gemma2-9b-it - meta-llama/llama-4-maverick-17b-128e-instruct - meta-llama/llama-4-scout-17b-16e-instruct - mistral-saba-24b - compound-beta - compound-beta-mini provider: type: string enum: - groq temperature: type: number description: >- This is the temperature that will be used for calls. Default is 0 to leverage caching for lower latency. minimum: 0 maximum: 2 maxTokens: type: number description: >- This is the max number of tokens that the assistant will be allowed to generate in each turn of the conversation. Default is 250. minimum: 50 maximum: 10000 emotionRecognitionEnabled: type: boolean description: >- This determines whether we detect user's emotion while they speak and send it as an additional info to model. Default `false` because the model is usually are good at understanding the user's emotion from text. @default false numFastTurns: type: number description: >- This sets how many turns at the start of the conversation to use a smaller, faster model from the same provider before switching to the primary model. Example, gpt-3.5-turbo if provider is openai. Default is 0. @default 0 minimum: 0 required: - model - provider InflectionAIModel: type: object properties: messages: description: This is the starting state for the conversation. type: array items: $ref: '#/components/schemas/OpenAIMessage' tools: type: array description: >- These are the tools that the assistant can use during the call. To use existing tools, use `toolIds`. Both `tools` and `toolIds` can be used together. items: oneOf: - $ref: '#/components/schemas/CreateApiRequestToolDTO' title: ApiRequestTool - $ref: '#/components/schemas/CreateBashToolDTO' title: BashTool - $ref: '#/components/schemas/CreateComputerToolDTO' title: ComputerTool - $ref: '#/components/schemas/CreateDtmfToolDTO' title: DtmfTool - $ref: '#/components/schemas/CreateEndCallToolDTO' title: EndCallTool - $ref: '#/components/schemas/CreateFunctionToolDTO' title: FunctionTool - $ref: >- #/components/schemas/CreateGoHighLevelCalendarAvailabilityToolDTO title: GoHighLevelCalendarAvailabilityTool - $ref: >- #/components/schemas/CreateGoHighLevelCalendarEventCreateToolDTO title: GoHighLevelCalendarEventCreateTool - $ref: '#/components/schemas/CreateGoHighLevelContactCreateToolDTO' title: GoHighLevelContactCreateTool - $ref: '#/components/schemas/CreateGoHighLevelContactGetToolDTO' title: GoHighLevelContactGetTool - $ref: >- #/components/schemas/CreateGoogleCalendarCheckAvailabilityToolDTO title: GoogleCalendarCheckAvailabilityTool - $ref: '#/components/schemas/CreateGoogleCalendarCreateEventToolDTO' title: GoogleCalendarCreateEventTool - $ref: '#/components/schemas/CreateGoogleSheetsRowAppendToolDTO' title: GoogleSheetsRowAppendTool - $ref: '#/components/schemas/CreateMcpToolDTO' title: McpTool - $ref: '#/components/schemas/CreateQueryToolDTO' title: QueryTool - $ref: '#/components/schemas/CreateSlackSendMessageToolDTO' title: SlackSendMessageTool - $ref: '#/components/schemas/CreateSmsToolDTO' title: SmsTool - $ref: '#/components/schemas/CreateTextEditorToolDTO' title: TextEditorTool - $ref: '#/components/schemas/CreateTransferCallToolDTO' title: TransferCallTool toolIds: description: >- These are the tools that the assistant can use during the call. To use transient tools, use `tools`. Both `tools` and `toolIds` can be used together. type: array items: type: string knowledgeBase: description: These are the options for the knowledge base. oneOf: - $ref: '#/components/schemas/CreateCustomKnowledgeBaseDTO' title: Custom knowledgeBaseId: type: string description: This is the ID of the knowledge base the model will use. model: type: string description: >- This is the name of the model. Ex. cognitivecomputations/dolphin-mixtral-8x7b enum: - inflection_3_pi provider: type: string enum: - inflection-ai temperature: type: number description: >- This is the temperature that will be used for calls. Default is 0 to leverage caching for lower latency. minimum: 0 maximum: 2 maxTokens: type: number description: >- This is the max number of tokens that the assistant will be allowed to generate in each turn of the conversation. Default is 250. minimum: 50 maximum: 10000 emotionRecognitionEnabled: type: boolean description: >- This determines whether we detect user's emotion while they speak and send it as an additional info to model. Default `false` because the model is usually are good at understanding the user's emotion from text. @default false numFastTurns: type: number description: >- This sets how many turns at the start of the conversation to use a smaller, faster model from the same provider before switching to the primary model. Example, gpt-3.5-turbo if provider is openai. Default is 0. @default 0 minimum: 0 required: - model - provider OpenAIModel: type: object properties: messages: description: This is the starting state for the conversation. type: array items: $ref: '#/components/schemas/OpenAIMessage' tools: type: array description: >- These are the tools that the assistant can use during the call. To use existing tools, use `toolIds`. Both `tools` and `toolIds` can be used together. items: oneOf: - $ref: '#/components/schemas/CreateApiRequestToolDTO' title: ApiRequestTool - $ref: '#/components/schemas/CreateBashToolDTO' title: BashTool - $ref: '#/components/schemas/CreateComputerToolDTO' title: ComputerTool - $ref: '#/components/schemas/CreateDtmfToolDTO' title: DtmfTool - $ref: '#/components/schemas/CreateEndCallToolDTO' title: EndCallTool - $ref: '#/components/schemas/CreateFunctionToolDTO' title: FunctionTool - $ref: >- #/components/schemas/CreateGoHighLevelCalendarAvailabilityToolDTO title: GoHighLevelCalendarAvailabilityTool - $ref: >- #/components/schemas/CreateGoHighLevelCalendarEventCreateToolDTO title: GoHighLevelCalendarEventCreateTool - $ref: '#/components/schemas/CreateGoHighLevelContactCreateToolDTO' title: GoHighLevelContactCreateTool - $ref: '#/components/schemas/CreateGoHighLevelContactGetToolDTO' title: GoHighLevelContactGetTool - $ref: >- #/components/schemas/CreateGoogleCalendarCheckAvailabilityToolDTO title: GoogleCalendarCheckAvailabilityTool - $ref: '#/components/schemas/CreateGoogleCalendarCreateEventToolDTO' title: GoogleCalendarCreateEventTool - $ref: '#/components/schemas/CreateGoogleSheetsRowAppendToolDTO' title: GoogleSheetsRowAppendTool - $ref: '#/components/schemas/CreateMcpToolDTO' title: McpTool - $ref: '#/components/schemas/CreateQueryToolDTO' title: QueryTool - $ref: '#/components/schemas/CreateSlackSendMessageToolDTO' title: SlackSendMessageTool - $ref: '#/components/schemas/CreateSmsToolDTO' title: SmsTool - $ref: '#/components/schemas/CreateTextEditorToolDTO' title: TextEditorTool - $ref: '#/components/schemas/CreateTransferCallToolDTO' title: TransferCallTool toolIds: description: >- These are the tools that the assistant can use during the call. To use transient tools, use `tools`. Both `tools` and `toolIds` can be used together. type: array items: type: string knowledgeBase: description: These are the options for the knowledge base. oneOf: - $ref: '#/components/schemas/CreateCustomKnowledgeBaseDTO' title: Custom knowledgeBaseId: type: string description: This is the ID of the knowledge base the model will use. provider: type: string description: This is the provider that will be used for the model. enum: - openai model: type: string description: >- This is the OpenAI model that will be used. When using cozmox OpenAI or your own Azure Credentials, you have the option to specify the region for the selected model. This shouldn't be specified unless you have a specific reason to do so. cozmox will automatically find the fastest region that make sense. This is helpful when you are required to comply with Data Residency rules. Learn more about Azure regions here https://azure.microsoft.com/en-us/explore/global-infrastructure/data-residency/. @default undefined enum: - gpt-4.1-2025-04-14 - gpt-4.1-mini-2025-04-14 - gpt-4.1-nano-2025-04-14 - gpt-4.1 - gpt-4.1-mini - gpt-4.1-nano - gpt-4.5-preview - chatgpt-4o-latest - o3 - o3-mini - o4-mini - o1-preview - o1-preview-2024-09-12 - o1-mini - o1-mini-2024-09-12 - gpt-4o-realtime-preview-2024-10-01 - gpt-4o-realtime-preview-2024-12-17 - gpt-4o-mini-realtime-preview-2024-12-17 - gpt-4o-mini-2024-07-18 - gpt-4o-mini - gpt-4o - gpt-4o-2024-05-13 - gpt-4o-2024-08-06 - gpt-4o-2024-11-20 - gpt-4-turbo - gpt-4-turbo-2024-04-09 - gpt-4-turbo-preview - gpt-4-0125-preview - gpt-4-1106-preview - gpt-4 - gpt-4-0613 - gpt-3.5-turbo - gpt-3.5-turbo-0125 - gpt-3.5-turbo-1106 - gpt-3.5-turbo-16k - gpt-3.5-turbo-0613 - gpt-4.1-2025-04-14:westus - gpt-4.1-2025-04-14:eastus2 - gpt-4.1-2025-04-14:eastus - gpt-4.1-2025-04-14:westus3 - gpt-4.1-2025-04-14:northcentralus - gpt-4.1-2025-04-14:southcentralus - gpt-4.1-mini-2025-04-14:westus - gpt-4.1-mini-2025-04-14:eastus2 - gpt-4.1-mini-2025-04-14:eastus - gpt-4.1-mini-2025-04-14:westus3 - gpt-4.1-mini-2025-04-14:northcentralus - gpt-4.1-mini-2025-04-14:southcentralus - gpt-4.1-nano-2025-04-14:westus - gpt-4.1-nano-2025-04-14:eastus2 - gpt-4.1-nano-2025-04-14:westus3 - gpt-4.1-nano-2025-04-14:northcentralus - gpt-4.1-nano-2025-04-14:southcentralus - gpt-4o-2024-11-20:swedencentral - gpt-4o-2024-11-20:westus - gpt-4o-2024-11-20:eastus2 - gpt-4o-2024-11-20:eastus - gpt-4o-2024-11-20:westus3 - gpt-4o-2024-11-20:southcentralus - gpt-4o-2024-08-06:westus - gpt-4o-2024-08-06:westus3 - gpt-4o-2024-08-06:eastus - gpt-4o-2024-08-06:eastus2 - gpt-4o-2024-08-06:northcentralus - gpt-4o-2024-08-06:southcentralus - gpt-4o-mini-2024-07-18:westus - gpt-4o-mini-2024-07-18:westus3 - gpt-4o-mini-2024-07-18:eastus - gpt-4o-mini-2024-07-18:eastus2 - gpt-4o-mini-2024-07-18:northcentralus - gpt-4o-mini-2024-07-18:southcentralus - gpt-4o-2024-05-13:eastus2 - gpt-4o-2024-05-13:eastus - gpt-4o-2024-05-13:northcentralus - gpt-4o-2024-05-13:southcentralus - gpt-4o-2024-05-13:westus3 - gpt-4o-2024-05-13:westus - gpt-4-turbo-2024-04-09:eastus2 - gpt-4-0125-preview:eastus - gpt-4-0125-preview:northcentralus - gpt-4-0125-preview:southcentralus - gpt-4-1106-preview:australia - gpt-4-1106-preview:canadaeast - gpt-4-1106-preview:france - gpt-4-1106-preview:india - gpt-4-1106-preview:norway - gpt-4-1106-preview:swedencentral - gpt-4-1106-preview:uk - gpt-4-1106-preview:westus - gpt-4-1106-preview:westus3 - gpt-4-0613:canadaeast - gpt-3.5-turbo-0125:canadaeast - gpt-3.5-turbo-0125:northcentralus - gpt-3.5-turbo-0125:southcentralus - gpt-3.5-turbo-1106:canadaeast - gpt-3.5-turbo-1106:westus fallbackModels: type: array description: >- These are the fallback models that will be used if the primary model fails. This shouldn't be specified unless you have a specific reason to do so. cozmox will automatically find the fastest fallbacks that make sense. enum: - gpt-4.1-2025-04-14 - gpt-4.1-mini-2025-04-14 - gpt-4.1-nano-2025-04-14 - gpt-4.1 - gpt-4.1-mini - gpt-4.1-nano - gpt-4.5-preview - chatgpt-4o-latest - o3 - o3-mini - o4-mini - o1-preview - o1-preview-2024-09-12 - o1-mini - o1-mini-2024-09-12 - gpt-4o-realtime-preview-2024-10-01 - gpt-4o-realtime-preview-2024-12-17 - gpt-4o-mini-realtime-preview-2024-12-17 - gpt-4o-mini-2024-07-18 - gpt-4o-mini - gpt-4o - gpt-4o-2024-05-13 - gpt-4o-2024-08-06 - gpt-4o-2024-11-20 - gpt-4-turbo - gpt-4-turbo-2024-04-09 - gpt-4-turbo-preview - gpt-4-0125-preview - gpt-4-1106-preview - gpt-4 - gpt-4-0613 - gpt-3.5-turbo - gpt-3.5-turbo-0125 - gpt-3.5-turbo-1106 - gpt-3.5-turbo-16k - gpt-3.5-turbo-0613 - gpt-4.1-2025-04-14:westus - gpt-4.1-2025-04-14:eastus2 - gpt-4.1-2025-04-14:eastus - gpt-4.1-2025-04-14:westus3 - gpt-4.1-2025-04-14:northcentralus - gpt-4.1-2025-04-14:southcentralus - gpt-4.1-mini-2025-04-14:westus - gpt-4.1-mini-2025-04-14:eastus2 - gpt-4.1-mini-2025-04-14:eastus - gpt-4.1-mini-2025-04-14:westus3 - gpt-4.1-mini-2025-04-14:northcentralus - gpt-4.1-mini-2025-04-14:southcentralus - gpt-4.1-nano-2025-04-14:westus - gpt-4.1-nano-2025-04-14:eastus2 - gpt-4.1-nano-2025-04-14:westus3 - gpt-4.1-nano-2025-04-14:northcentralus - gpt-4.1-nano-2025-04-14:southcentralus - gpt-4o-2024-11-20:swedencentral - gpt-4o-2024-11-20:westus - gpt-4o-2024-11-20:eastus2 - gpt-4o-2024-11-20:eastus - gpt-4o-2024-11-20:westus3 - gpt-4o-2024-11-20:southcentralus - gpt-4o-2024-08-06:westus - gpt-4o-2024-08-06:westus3 - gpt-4o-2024-08-06:eastus - gpt-4o-2024-08-06:eastus2 - gpt-4o-2024-08-06:northcentralus - gpt-4o-2024-08-06:southcentralus - gpt-4o-mini-2024-07-18:westus - gpt-4o-mini-2024-07-18:westus3 - gpt-4o-mini-2024-07-18:eastus - gpt-4o-mini-2024-07-18:eastus2 - gpt-4o-mini-2024-07-18:northcentralus - gpt-4o-mini-2024-07-18:southcentralus - gpt-4o-2024-05-13:eastus2 - gpt-4o-2024-05-13:eastus - gpt-4o-2024-05-13:northcentralus - gpt-4o-2024-05-13:southcentralus - gpt-4o-2024-05-13:westus3 - gpt-4o-2024-05-13:westus - gpt-4-turbo-2024-04-09:eastus2 - gpt-4-0125-preview:eastus - gpt-4-0125-preview:northcentralus - gpt-4-0125-preview:southcentralus - gpt-4-1106-preview:australia - gpt-4-1106-preview:canadaeast - gpt-4-1106-preview:france - gpt-4-1106-preview:india - gpt-4-1106-preview:norway - gpt-4-1106-preview:swedencentral - gpt-4-1106-preview:uk - gpt-4-1106-preview:westus - gpt-4-1106-preview:westus3 - gpt-4-0613:canadaeast - gpt-3.5-turbo-0125:canadaeast - gpt-3.5-turbo-0125:northcentralus - gpt-3.5-turbo-0125:southcentralus - gpt-3.5-turbo-1106:canadaeast - gpt-3.5-turbo-1106:westus example: - gpt-4-0125-preview - gpt-4-0613 items: type: string enum: - gpt-4.1-2025-04-14 - gpt-4.1-mini-2025-04-14 - gpt-4.1-nano-2025-04-14 - gpt-4.1 - gpt-4.1-mini - gpt-4.1-nano - gpt-4.5-preview - chatgpt-4o-latest - o3 - o3-mini - o4-mini - o1-preview - o1-preview-2024-09-12 - o1-mini - o1-mini-2024-09-12 - gpt-4o-realtime-preview-2024-10-01 - gpt-4o-realtime-preview-2024-12-17 - gpt-4o-mini-realtime-preview-2024-12-17 - gpt-4o-mini-2024-07-18 - gpt-4o-mini - gpt-4o - gpt-4o-2024-05-13 - gpt-4o-2024-08-06 - gpt-4o-2024-11-20 - gpt-4-turbo - gpt-4-turbo-2024-04-09 - gpt-4-turbo-preview - gpt-4-0125-preview - gpt-4-1106-preview - gpt-4 - gpt-4-0613 - gpt-3.5-turbo - gpt-3.5-turbo-0125 - gpt-3.5-turbo-1106 - gpt-3.5-turbo-16k - gpt-3.5-turbo-0613 - gpt-4.1-2025-04-14:westus - gpt-4.1-2025-04-14:eastus2 - gpt-4.1-2025-04-14:eastus - gpt-4.1-2025-04-14:westus3 - gpt-4.1-2025-04-14:northcentralus - gpt-4.1-2025-04-14:southcentralus - gpt-4.1-mini-2025-04-14:westus - gpt-4.1-mini-2025-04-14:eastus2 - gpt-4.1-mini-2025-04-14:eastus - gpt-4.1-mini-2025-04-14:westus3 - gpt-4.1-mini-2025-04-14:northcentralus - gpt-4.1-mini-2025-04-14:southcentralus - gpt-4.1-nano-2025-04-14:westus - gpt-4.1-nano-2025-04-14:eastus2 - gpt-4.1-nano-2025-04-14:westus3 - gpt-4.1-nano-2025-04-14:northcentralus - gpt-4.1-nano-2025-04-14:southcentralus - gpt-4o-2024-11-20:swedencentral - gpt-4o-2024-11-20:westus - gpt-4o-2024-11-20:eastus2 - gpt-4o-2024-11-20:eastus - gpt-4o-2024-11-20:westus3 - gpt-4o-2024-11-20:southcentralus - gpt-4o-2024-08-06:westus - gpt-4o-2024-08-06:westus3 - gpt-4o-2024-08-06:eastus - gpt-4o-2024-08-06:eastus2 - gpt-4o-2024-08-06:northcentralus - gpt-4o-2024-08-06:southcentralus - gpt-4o-mini-2024-07-18:westus - gpt-4o-mini-2024-07-18:westus3 - gpt-4o-mini-2024-07-18:eastus - gpt-4o-mini-2024-07-18:eastus2 - gpt-4o-mini-2024-07-18:northcentralus - gpt-4o-mini-2024-07-18:southcentralus - gpt-4o-2024-05-13:eastus2 - gpt-4o-2024-05-13:eastus - gpt-4o-2024-05-13:northcentralus - gpt-4o-2024-05-13:southcentralus - gpt-4o-2024-05-13:westus3 - gpt-4o-2024-05-13:westus - gpt-4-turbo-2024-04-09:eastus2 - gpt-4-0125-preview:eastus - gpt-4-0125-preview:northcentralus - gpt-4-0125-preview:southcentralus - gpt-4-1106-preview:australia - gpt-4-1106-preview:canadaeast - gpt-4-1106-preview:france - gpt-4-1106-preview:india - gpt-4-1106-preview:norway - gpt-4-1106-preview:swedencentral - gpt-4-1106-preview:uk - gpt-4-1106-preview:westus - gpt-4-1106-preview:westus3 - gpt-4-0613:canadaeast - gpt-3.5-turbo-0125:canadaeast - gpt-3.5-turbo-0125:northcentralus - gpt-3.5-turbo-0125:southcentralus - gpt-3.5-turbo-1106:canadaeast - gpt-3.5-turbo-1106:westus toolStrictCompatibilityMode: type: string description: >- Azure OpenAI doesn't support `maxLength` right now https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/structured-outputs?tabs=python-secure%2Cdotnet-entra-id&pivots=programming-language-csharp#unsupported-type-specific-keywords. Need to strip. - `strip-parameters-with-unsupported-validation` will strip parameters with unsupported validation. - `strip-unsupported-validation` will keep the parameters but strip unsupported validation. @default `strip-unsupported-validation` enum: - strip-parameters-with-unsupported-validation - strip-unsupported-validation temperature: type: number description: >- This is the temperature that will be used for calls. Default is 0 to leverage caching for lower latency. minimum: 0 maximum: 2 maxTokens: type: number description: >- This is the max number of tokens that the assistant will be allowed to generate in each turn of the conversation. Default is 250. minimum: 50 maximum: 10000 emotionRecognitionEnabled: type: boolean description: >- This determines whether we detect user's emotion while they speak and send it as an additional info to model. Default `false` because the model is usually are good at understanding the user's emotion from text. @default false numFastTurns: type: number description: >- This sets how many turns at the start of the conversation to use a smaller, faster model from the same provider before switching to the primary model. Example, gpt-3.5-turbo if provider is openai. Default is 0. @default 0 minimum: 0 required: - provider - model OpenRouterModel: type: object properties: messages: description: This is the starting state for the conversation. type: array items: $ref: '#/components/schemas/OpenAIMessage' tools: type: array description: >- These are the tools that the assistant can use during the call. To use existing tools, use `toolIds`. Both `tools` and `toolIds` can be used together. items: oneOf: - $ref: '#/components/schemas/CreateApiRequestToolDTO' title: ApiRequestTool - $ref: '#/components/schemas/CreateBashToolDTO' title: BashTool - $ref: '#/components/schemas/CreateComputerToolDTO' title: ComputerTool - $ref: '#/components/schemas/CreateDtmfToolDTO' title: DtmfTool - $ref: '#/components/schemas/CreateEndCallToolDTO' title: EndCallTool - $ref: '#/components/schemas/CreateFunctionToolDTO' title: FunctionTool - $ref: >- #/components/schemas/CreateGoHighLevelCalendarAvailabilityToolDTO title: GoHighLevelCalendarAvailabilityTool - $ref: >- #/components/schemas/CreateGoHighLevelCalendarEventCreateToolDTO title: GoHighLevelCalendarEventCreateTool - $ref: '#/components/schemas/CreateGoHighLevelContactCreateToolDTO' title: GoHighLevelContactCreateTool - $ref: '#/components/schemas/CreateGoHighLevelContactGetToolDTO' title: GoHighLevelContactGetTool - $ref: >- #/components/schemas/CreateGoogleCalendarCheckAvailabilityToolDTO title: GoogleCalendarCheckAvailabilityTool - $ref: '#/components/schemas/CreateGoogleCalendarCreateEventToolDTO' title: GoogleCalendarCreateEventTool - $ref: '#/components/schemas/CreateGoogleSheetsRowAppendToolDTO' title: GoogleSheetsRowAppendTool - $ref: '#/components/schemas/CreateMcpToolDTO' title: McpTool - $ref: '#/components/schemas/CreateQueryToolDTO' title: QueryTool - $ref: '#/components/schemas/CreateSlackSendMessageToolDTO' title: SlackSendMessageTool - $ref: '#/components/schemas/CreateSmsToolDTO' title: SmsTool - $ref: '#/components/schemas/CreateTextEditorToolDTO' title: TextEditorTool - $ref: '#/components/schemas/CreateTransferCallToolDTO' title: TransferCallTool toolIds: description: >- These are the tools that the assistant can use during the call. To use transient tools, use `tools`. Both `tools` and `toolIds` can be used together. type: array items: type: string knowledgeBase: description: These are the options for the knowledge base. oneOf: - $ref: '#/components/schemas/CreateCustomKnowledgeBaseDTO' title: Custom knowledgeBaseId: type: string description: This is the ID of the knowledge base the model will use. provider: type: string enum: - openrouter model: type: string description: >- This is the name of the model. Ex. cognitivecomputations/dolphin-mixtral-8x7b temperature: type: number description: >- This is the temperature that will be used for calls. Default is 0 to leverage caching for lower latency. minimum: 0 maximum: 2 maxTokens: type: number description: >- This is the max number of tokens that the assistant will be allowed to generate in each turn of the conversation. Default is 250. minimum: 50 maximum: 10000 emotionRecognitionEnabled: type: boolean description: >- This determines whether we detect user's emotion while they speak and send it as an additional info to model. Default `false` because the model is usually are good at understanding the user's emotion from text. @default false numFastTurns: type: number description: >- This sets how many turns at the start of the conversation to use a smaller, faster model from the same provider before switching to the primary model. Example, gpt-3.5-turbo if provider is openai. Default is 0. @default 0 minimum: 0 required: - provider - model PerplexityAIModel: type: object properties: messages: description: This is the starting state for the conversation. type: array items: $ref: '#/components/schemas/OpenAIMessage' tools: type: array description: >- These are the tools that the assistant can use during the call. To use existing tools, use `toolIds`. Both `tools` and `toolIds` can be used together. items: oneOf: - $ref: '#/components/schemas/CreateApiRequestToolDTO' title: ApiRequestTool - $ref: '#/components/schemas/CreateBashToolDTO' title: BashTool - $ref: '#/components/schemas/CreateComputerToolDTO' title: ComputerTool - $ref: '#/components/schemas/CreateDtmfToolDTO' title: DtmfTool - $ref: '#/components/schemas/CreateEndCallToolDTO' title: EndCallTool - $ref: '#/components/schemas/CreateFunctionToolDTO' title: FunctionTool - $ref: >- #/components/schemas/CreateGoHighLevelCalendarAvailabilityToolDTO title: GoHighLevelCalendarAvailabilityTool - $ref: >- #/components/schemas/CreateGoHighLevelCalendarEventCreateToolDTO title: GoHighLevelCalendarEventCreateTool - $ref: '#/components/schemas/CreateGoHighLevelContactCreateToolDTO' title: GoHighLevelContactCreateTool - $ref: '#/components/schemas/CreateGoHighLevelContactGetToolDTO' title: GoHighLevelContactGetTool - $ref: >- #/components/schemas/CreateGoogleCalendarCheckAvailabilityToolDTO title: GoogleCalendarCheckAvailabilityTool - $ref: '#/components/schemas/CreateGoogleCalendarCreateEventToolDTO' title: GoogleCalendarCreateEventTool - $ref: '#/components/schemas/CreateGoogleSheetsRowAppendToolDTO' title: GoogleSheetsRowAppendTool - $ref: '#/components/schemas/CreateMcpToolDTO' title: McpTool - $ref: '#/components/schemas/CreateQueryToolDTO' title: QueryTool - $ref: '#/components/schemas/CreateSlackSendMessageToolDTO' title: SlackSendMessageTool - $ref: '#/components/schemas/CreateSmsToolDTO' title: SmsTool - $ref: '#/components/schemas/CreateTextEditorToolDTO' title: TextEditorTool - $ref: '#/components/schemas/CreateTransferCallToolDTO' title: TransferCallTool toolIds: description: >- These are the tools that the assistant can use during the call. To use transient tools, use `tools`. Both `tools` and `toolIds` can be used together. type: array items: type: string knowledgeBase: description: These are the options for the knowledge base. oneOf: - $ref: '#/components/schemas/CreateCustomKnowledgeBaseDTO' title: Custom knowledgeBaseId: type: string description: This is the ID of the knowledge base the model will use. provider: type: string enum: - perplexity-ai model: type: string description: >- This is the name of the model. Ex. cognitivecomputations/dolphin-mixtral-8x7b temperature: type: number description: >- This is the temperature that will be used for calls. Default is 0 to leverage caching for lower latency. minimum: 0 maximum: 2 maxTokens: type: number description: >- This is the max number of tokens that the assistant will be allowed to generate in each turn of the conversation. Default is 250. minimum: 50 maximum: 10000 emotionRecognitionEnabled: type: boolean description: >- This determines whether we detect user's emotion while they speak and send it as an additional info to model. Default `false` because the model is usually are good at understanding the user's emotion from text. @default false numFastTurns: type: number description: >- This sets how many turns at the start of the conversation to use a smaller, faster model from the same provider before switching to the primary model. Example, gpt-3.5-turbo if provider is openai. Default is 0. @default 0 minimum: 0 required: - provider - model TogetherAIModel: type: object properties: messages: description: This is the starting state for the conversation. type: array items: $ref: '#/components/schemas/OpenAIMessage' tools: type: array description: >- These are the tools that the assistant can use during the call. To use existing tools, use `toolIds`. Both `tools` and `toolIds` can be used together. items: oneOf: - $ref: '#/components/schemas/CreateApiRequestToolDTO' title: ApiRequestTool - $ref: '#/components/schemas/CreateBashToolDTO' title: BashTool - $ref: '#/components/schemas/CreateComputerToolDTO' title: ComputerTool - $ref: '#/components/schemas/CreateDtmfToolDTO' title: DtmfTool - $ref: '#/components/schemas/CreateEndCallToolDTO' title: EndCallTool - $ref: '#/components/schemas/CreateFunctionToolDTO' title: FunctionTool - $ref: >- #/components/schemas/CreateGoHighLevelCalendarAvailabilityToolDTO title: GoHighLevelCalendarAvailabilityTool - $ref: >- #/components/schemas/CreateGoHighLevelCalendarEventCreateToolDTO title: GoHighLevelCalendarEventCreateTool - $ref: '#/components/schemas/CreateGoHighLevelContactCreateToolDTO' title: GoHighLevelContactCreateTool - $ref: '#/components/schemas/CreateGoHighLevelContactGetToolDTO' title: GoHighLevelContactGetTool - $ref: >- #/components/schemas/CreateGoogleCalendarCheckAvailabilityToolDTO title: GoogleCalendarCheckAvailabilityTool - $ref: '#/components/schemas/CreateGoogleCalendarCreateEventToolDTO' title: GoogleCalendarCreateEventTool - $ref: '#/components/schemas/CreateGoogleSheetsRowAppendToolDTO' title: GoogleSheetsRowAppendTool - $ref: '#/components/schemas/CreateMcpToolDTO' title: McpTool - $ref: '#/components/schemas/CreateQueryToolDTO' title: QueryTool - $ref: '#/components/schemas/CreateSlackSendMessageToolDTO' title: SlackSendMessageTool - $ref: '#/components/schemas/CreateSmsToolDTO' title: SmsTool - $ref: '#/components/schemas/CreateTextEditorToolDTO' title: TextEditorTool - $ref: '#/components/schemas/CreateTransferCallToolDTO' title: TransferCallTool toolIds: description: >- These are the tools that the assistant can use during the call. To use transient tools, use `tools`. Both `tools` and `toolIds` can be used together. type: array items: type: string knowledgeBase: description: These are the options for the knowledge base. oneOf: - $ref: '#/components/schemas/CreateCustomKnowledgeBaseDTO' title: Custom knowledgeBaseId: type: string description: This is the ID of the knowledge base the model will use. provider: type: string enum: - together-ai model: type: string description: >- This is the name of the model. Ex. cognitivecomputations/dolphin-mixtral-8x7b temperature: type: number description: >- This is the temperature that will be used for calls. Default is 0 to leverage caching for lower latency. minimum: 0 maximum: 2 maxTokens: type: number description: >- This is the max number of tokens that the assistant will be allowed to generate in each turn of the conversation. Default is 250. minimum: 50 maximum: 10000 emotionRecognitionEnabled: type: boolean description: >- This determines whether we detect user's emotion while they speak and send it as an additional info to model. Default `false` because the model is usually are good at understanding the user's emotion from text. @default false numFastTurns: type: number description: >- This sets how many turns at the start of the conversation to use a smaller, faster model from the same provider before switching to the primary model. Example, gpt-3.5-turbo if provider is openai. Default is 0. @default 0 minimum: 0 required: - provider - model XaiModel: type: object properties: messages: description: This is the starting state for the conversation. type: array items: $ref: '#/components/schemas/OpenAIMessage' tools: type: array description: >- These are the tools that the assistant can use during the call. To use existing tools, use `toolIds`. Both `tools` and `toolIds` can be used together. items: oneOf: - $ref: '#/components/schemas/CreateApiRequestToolDTO' title: ApiRequestTool - $ref: '#/components/schemas/CreateBashToolDTO' title: BashTool - $ref: '#/components/schemas/CreateComputerToolDTO' title: ComputerTool - $ref: '#/components/schemas/CreateDtmfToolDTO' title: DtmfTool - $ref: '#/components/schemas/CreateEndCallToolDTO' title: EndCallTool - $ref: '#/components/schemas/CreateFunctionToolDTO' title: FunctionTool - $ref: >- #/components/schemas/CreateGoHighLevelCalendarAvailabilityToolDTO title: GoHighLevelCalendarAvailabilityTool - $ref: >- #/components/schemas/CreateGoHighLevelCalendarEventCreateToolDTO title: GoHighLevelCalendarEventCreateTool - $ref: '#/components/schemas/CreateGoHighLevelContactCreateToolDTO' title: GoHighLevelContactCreateTool - $ref: '#/components/schemas/CreateGoHighLevelContactGetToolDTO' title: GoHighLevelContactGetTool - $ref: >- #/components/schemas/CreateGoogleCalendarCheckAvailabilityToolDTO title: GoogleCalendarCheckAvailabilityTool - $ref: '#/components/schemas/CreateGoogleCalendarCreateEventToolDTO' title: GoogleCalendarCreateEventTool - $ref: '#/components/schemas/CreateGoogleSheetsRowAppendToolDTO' title: GoogleSheetsRowAppendTool - $ref: '#/components/schemas/CreateMcpToolDTO' title: McpTool - $ref: '#/components/schemas/CreateQueryToolDTO' title: QueryTool - $ref: '#/components/schemas/CreateSlackSendMessageToolDTO' title: SlackSendMessageTool - $ref: '#/components/schemas/CreateSmsToolDTO' title: SmsTool - $ref: '#/components/schemas/CreateTextEditorToolDTO' title: TextEditorTool - $ref: '#/components/schemas/CreateTransferCallToolDTO' title: TransferCallTool toolIds: description: >- These are the tools that the assistant can use during the call. To use transient tools, use `tools`. Both `tools` and `toolIds` can be used together. type: array items: type: string knowledgeBase: description: These are the options for the knowledge base. oneOf: - $ref: '#/components/schemas/CreateCustomKnowledgeBaseDTO' title: Custom knowledgeBaseId: type: string description: This is the ID of the knowledge base the model will use. model: type: string description: >- This is the name of the model. Ex. cognitivecomputations/dolphin-mixtral-8x7b enum: - grok-beta - grok-2 - grok-3 provider: type: string enum: - xai temperature: type: number description: >- This is the temperature that will be used for calls. Default is 0 to leverage caching for lower latency. minimum: 0 maximum: 2 maxTokens: type: number description: >- This is the max number of tokens that the assistant will be allowed to generate in each turn of the conversation. Default is 250. minimum: 50 maximum: 10000 emotionRecognitionEnabled: type: boolean description: >- This determines whether we detect user's emotion while they speak and send it as an additional info to model. Default `false` because the model is usually are good at understanding the user's emotion from text. @default false numFastTurns: type: number description: >- This sets how many turns at the start of the conversation to use a smaller, faster model from the same provider before switching to the primary model. Example, gpt-3.5-turbo if provider is openai. Default is 0. @default 0 minimum: 0 required: - model - provider AzureVoice: type: object properties: cachingEnabled: type: boolean description: This is the flag to toggle voice caching for the assistant. example: true default: true provider: type: string description: This is the voice provider that will be used. enum: - azure voiceId: description: This is the provider-specific ID that will be used. oneOf: - type: string enum: - andrew - brian - emma title: Preset Voice Options - type: string title: Azure Voice ID chunkPlan: description: >- This is the plan for chunking the model output before it is sent to the voice provider. allOf: - $ref: '#/components/schemas/ChunkPlan' speed: type: number description: This is the speed multiplier that will be used. minimum: 0.5 maximum: 2 fallbackPlan: description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. allOf: - $ref: '#/components/schemas/FallbackPlan' required: - provider - voiceId CartesiaVoice: type: object properties: cachingEnabled: type: boolean description: This is the flag to toggle voice caching for the assistant. example: true default: true provider: type: string description: This is the voice provider that will be used. enum: - cartesia voiceId: type: string description: The ID of the particular voice you want to use. model: type: string description: >- This is the model that will be used. This is optional and will default to the correct model for the voiceId. enum: - sonic-2 - sonic-english - sonic-multilingual - sonic-preview - sonic example: sonic-english language: type: string description: >- This is the language that will be used. This is optional and will default to the correct language for the voiceId. enum: - en - de - es - fr - ja - pt - zh - hi - it - ko - nl - pl - ru - sv - tr example: en experimentalControls: description: Experimental controls for Cartesia voice generation allOf: - $ref: '#/components/schemas/CartesiaExperimentalControls' chunkPlan: description: >- This is the plan for chunking the model output before it is sent to the voice provider. allOf: - $ref: '#/components/schemas/ChunkPlan' fallbackPlan: description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. allOf: - $ref: '#/components/schemas/FallbackPlan' required: - provider - voiceId CustomVoice: type: object properties: cachingEnabled: type: boolean description: This is the flag to toggle voice caching for the assistant. example: true default: true provider: type: string description: >- This is the voice provider that will be used. Use `custom-voice` for providers that are not natively supported. enum: - custom-voice chunkPlan: description: >- This is the plan for chunking the model output before it is sent to the voice provider. allOf: - $ref: '#/components/schemas/ChunkPlan' server: description: >- This is where the voice request will be sent. Request Example: POST https://{server.url} Content-Type: application/json { "message": { "type": "voice-request", "text": "Hello, world!", "sampleRate": 24000, ...other metadata about the call... } } Response Expected: 1-channel 16-bit raw PCM audio at the sample rate specified in the request. Here is how the response will be piped to the transport: ``` response.on('data', (chunk: Buffer) => { outputStream.write(chunk); }); ``` allOf: - $ref: '#/components/schemas/Server' fallbackPlan: description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. allOf: - $ref: '#/components/schemas/FallbackPlan' required: - provider - server DeepgramVoice: type: object properties: cachingEnabled: type: boolean description: This is the flag to toggle voice caching for the assistant. example: true default: true provider: type: string description: This is the voice provider that will be used. enum: - deepgram voiceId: type: string description: This is the provider-specific ID that will be used. enum: - asteria - luna - stella - athena - hera - orion - arcas - perseus - angus - orpheus - helios - zeus - thalia - andromeda - helena - apollo - arcas - aries - amalthea - asteria - athena - atlas - aurora - callista - cora - cordelia - delia - draco - electra - harmonia - hera - hermes - hyperion - iris - janus - juno - jupiter - luna - mars - minerva - neptune - odysseus - ophelia - orion - orpheus - pandora - phoebe - pluto - saturn - selene - theia - vesta - zeus title: This is the Deepgram Voice ID model: type: string description: >- This is the model that will be used. Defaults to 'aura-2' when not specified. enum: - aura - aura-2 example: aura-2 mipOptOut: type: boolean description: >- If set to true, this will add mip_opt_out=true as a query parameter of all API requests. See https://developers.deepgram.com/docs/the-deepgram-model-improvement-partnership-program#want-to-opt-out This will only be used if you are using your own Deepgram API key. @default false example: false default: false chunkPlan: description: >- This is the plan for chunking the model output before it is sent to the voice provider. allOf: - $ref: '#/components/schemas/ChunkPlan' fallbackPlan: description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. allOf: - $ref: '#/components/schemas/FallbackPlan' required: - provider - voiceId ElevenLabsVoice: type: object properties: cachingEnabled: type: boolean description: This is the flag to toggle voice caching for the assistant. example: true default: true provider: type: string description: This is the voice provider that will be used. enum: - 11labs voiceId: description: >- This is the provider-specific ID that will be used. Ensure the Voice is present in your 11Labs Voice Library. oneOf: - type: string enum: - burt - marissa - andrea - sarah - phillip - steve - joseph - myra - paula - ryan - drew - paul - mrb - matilda - mark title: Preset Voice Options - type: string title: 11Labs Voice ID stability: type: number description: Defines the stability for voice settings. minimum: 0 maximum: 1 example: 0.5 similarityBoost: type: number description: Defines the similarity boost for voice settings. minimum: 0 maximum: 1 example: 0.75 style: type: number description: Defines the style for voice settings. minimum: 0 maximum: 1 example: 0 useSpeakerBoost: type: boolean description: Defines the use speaker boost for voice settings. example: false speed: type: number description: Defines the speed for voice settings. minimum: 0.7 maximum: 1.2 example: 0.9 optimizeStreamingLatency: type: number description: >- Defines the optimize streaming latency for voice settings. Defaults to 3. minimum: 0 maximum: 4 example: 3 enableSsmlParsing: type: boolean description: >- This enables the use of https://elevenlabs.io/docs/speech-synthesis/prompting#pronunciation. Defaults to false to save latency. @default false example: false autoMode: type: boolean description: Defines the auto mode for voice settings. Defaults to false. example: false model: type: string description: >- This is the model that will be used. Defaults to 'eleven_turbo_v2' if not specified. enum: - eleven_multilingual_v2 - eleven_turbo_v2 - eleven_turbo_v2_5 - eleven_flash_v2 - eleven_flash_v2_5 - eleven_monolingual_v1 example: eleven_turbo_v2_5 chunkPlan: description: >- This is the plan for chunking the model output before it is sent to the voice provider. allOf: - $ref: '#/components/schemas/ChunkPlan' language: type: string description: >- This is the language (ISO 639-1) that is enforced for the model. Currently only Turbo v2.5 supports language enforcement. For other models, an error will be returned if language code is provided. fallbackPlan: description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. allOf: - $ref: '#/components/schemas/FallbackPlan' required: - provider - voiceId HumeVoice: type: object properties: cachingEnabled: type: boolean description: This is the flag to toggle voice caching for the assistant. example: true default: true provider: type: string description: This is the voice provider that will be used. enum: - hume model: type: string description: This is the model that will be used. enum: - octave example: octave voiceId: type: string description: The ID of the particular voice you want to use. isCustomHumeVoice: type: boolean description: >- Indicates whether the chosen voice is a preset Hume AI voice or a custom voice. example: false chunkPlan: description: >- This is the plan for chunking the model output before it is sent to the voice provider. allOf: - $ref: '#/components/schemas/ChunkPlan' description: type: string description: >- Natural language instructions describing how the synthesized speech should sound, including but not limited to tone, intonation, pacing, and accent (e.g., 'a soft, gentle voice with a strong British accent'). If a Voice is specified in the request, this description serves as acting instructions. If no Voice is specified, a new voice is generated based on this description. fallbackPlan: description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. allOf: - $ref: '#/components/schemas/FallbackPlan' required: - provider - voiceId LMNTVoice: type: object properties: cachingEnabled: type: boolean description: This is the flag to toggle voice caching for the assistant. example: true default: true provider: type: string description: This is the voice provider that will be used. enum: - lmnt voiceId: description: This is the provider-specific ID that will be used. oneOf: - type: string enum: - amy - ansel - autumn - ava - brandon - caleb - cassian - chloe - dalton - daniel - dustin - elowen - evander - huxley - james - juniper - kennedy - lauren - leah - lily - lucas - magnus - miles - morgan - natalie - nathan - noah - nyssa - oliver - paige - ryan - sadie - sophie - stella - terrence - tyler - vesper - violet - warrick - zain - zeke - zoe title: Preset Voice Options - type: string title: LMNT Voice ID speed: type: number description: This is the speed multiplier that will be used. minimum: 0.25 maximum: 2 example: null language: description: Two letter ISO 639-1 language code. Use "auto" for auto-detection. enum: - aa - ab - ae - af - ak - am - an - ar - as - av - ay - az - ba - be - bg - bh - bi - bm - bn - bo - br - bs - ca - ce - ch - co - cr - cs - cu - cv - cy - da - de - dv - dz - ee - el - en - eo - es - et - eu - fa - ff - fi - fj - fo - fr - fy - ga - gd - gl - gn - gu - gv - ha - he - hi - ho - hr - ht - hu - hy - hz - ia - id - ie - ig - ii - ik - io - is - it - iu - ja - jv - ka - kg - ki - kj - kk - kl - km - kn - ko - kr - ks - ku - kv - kw - ky - la - lb - lg - li - ln - lo - lt - lu - lv - mg - mh - mi - mk - ml - mn - mr - ms - mt - my - na - nb - nd - ne - ng - nl - nn - 'no' - nr - nv - ny - oc - oj - om - or - os - pa - pi - pl - ps - pt - qu - rm - rn - ro - ru - rw - sa - sc - sd - se - sg - si - sk - sl - sm - sn - so - sq - sr - ss - st - su - sv - sw - ta - te - tg - th - ti - tk - tl - tn - to - tr - ts - tt - tw - ty - ug - uk - ur - uz - ve - vi - vo - wa - wo - xh - yi - yue - yo - za - zh - zu - auto example: en oneOf: - type: string enum: - aa - ab - ae - af - ak - am - an - ar - as - av - ay - az - ba - be - bg - bh - bi - bm - bn - bo - br - bs - ca - ce - ch - co - cr - cs - cu - cv - cy - da - de - dv - dz - ee - el - en - eo - es - et - eu - fa - ff - fi - fj - fo - fr - fy - ga - gd - gl - gn - gu - gv - ha - he - hi - ho - hr - ht - hu - hy - hz - ia - id - ie - ig - ii - ik - io - is - it - iu - ja - jv - ka - kg - ki - kj - kk - kl - km - kn - ko - kr - ks - ku - kv - kw - ky - la - lb - lg - li - ln - lo - lt - lu - lv - mg - mh - mi - mk - ml - mn - mr - ms - mt - my - na - nb - nd - ne - ng - nl - nn - 'no' - nr - nv - ny - oc - oj - om - or - os - pa - pi - pl - ps - pt - qu - rm - rn - ro - ru - rw - sa - sc - sd - se - sg - si - sk - sl - sm - sn - so - sq - sr - ss - st - su - sv - sw - ta - te - tg - th - ti - tk - tl - tn - to - tr - ts - tt - tw - ty - ug - uk - ur - uz - ve - vi - vo - wa - wo - xh - yi - yue - yo - za - zh - zu title: ISO 639-1 Language Code - type: string enum: - auto title: Auto-detect chunkPlan: description: >- This is the plan for chunking the model output before it is sent to the voice provider. allOf: - $ref: '#/components/schemas/ChunkPlan' fallbackPlan: description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. allOf: - $ref: '#/components/schemas/FallbackPlan' required: - provider - voiceId NeuphonicVoice: type: object properties: cachingEnabled: type: boolean description: This is the flag to toggle voice caching for the assistant. example: true default: true provider: type: string description: This is the voice provider that will be used. enum: - neuphonic voiceId: description: This is the provider-specific ID that will be used. oneOf: - type: string enum: - test title: Preset Voice Options - type: string title: Neuphonic Voice ID model: type: string description: >- This is the model that will be used. Defaults to 'neu_fast' if not specified. enum: - neu_hq - neu_fast example: neu_fast language: type: object description: This is the language (ISO 639-1) that is enforced for the model. example: en speed: type: number description: This is the speed multiplier that will be used. minimum: 0.25 maximum: 2 example: null chunkPlan: description: >- This is the plan for chunking the model output before it is sent to the voice provider. allOf: - $ref: '#/components/schemas/ChunkPlan' fallbackPlan: description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. allOf: - $ref: '#/components/schemas/FallbackPlan' required: - provider - voiceId - language OpenAIVoice: type: object properties: cachingEnabled: type: boolean description: This is the flag to toggle voice caching for the assistant. example: true default: true provider: type: string description: This is the voice provider that will be used. enum: - openai voiceId: description: >- This is the provider-specific ID that will be used. Please note that ash, ballad, coral, sage, and verse may only be used with realtime models. oneOf: - type: string enum: - alloy - echo - fable - onyx - nova - shimmer title: Preset Voice Options - type: string title: OpenAI Voice ID model: type: string description: This is the model that will be used for text-to-speech. enum: - tts-1 - tts-1-hd - gpt-4o-mini-tts instructions: type: string description: >- This is a prompt that allows you to control the voice of your generated audio. Does not work with 'tts-1' or 'tts-1-hd' models. maxLength: 10000 speed: type: number description: This is the speed multiplier that will be used. minimum: 0.25 maximum: 4 example: null chunkPlan: description: >- This is the plan for chunking the model output before it is sent to the voice provider. allOf: - $ref: '#/components/schemas/ChunkPlan' fallbackPlan: description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. allOf: - $ref: '#/components/schemas/FallbackPlan' required: - provider - voiceId PlayHTVoice: type: object properties: cachingEnabled: type: boolean description: This is the flag to toggle voice caching for the assistant. example: true default: true provider: type: string description: This is the voice provider that will be used. enum: - playht voiceId: description: This is the provider-specific ID that will be used. oneOf: - type: string enum: - jennifer - melissa - will - chris - matt - jack - ruby - davis - donna - michael title: Preset Voice Options - type: string title: PlayHT Voice ID speed: type: number description: This is the speed multiplier that will be used. minimum: 0.1 maximum: 5 example: null temperature: type: number description: >- A floating point number between 0, exclusive, and 2, inclusive. If equal to null or not provided, the model's default temperature will be used. The temperature parameter controls variance. Lower temperatures result in more predictable results, higher temperatures allow each run to vary more, so the voice may sound less like the baseline voice. minimum: 0.1 maximum: 2 example: null emotion: type: string description: An emotion to be applied to the speech. enum: - female_happy - female_sad - female_angry - female_fearful - female_disgust - female_surprised - male_happy - male_sad - male_angry - male_fearful - male_disgust - male_surprised example: null voiceGuidance: type: number description: >- A number between 1 and 6. Use lower numbers to reduce how unique your chosen voice will be compared to other voices. minimum: 1 maximum: 6 example: null styleGuidance: type: number description: >- A number between 1 and 30. Use lower numbers to to reduce how strong your chosen emotion will be. Higher numbers will create a very emotional performance. minimum: 1 maximum: 30 example: null textGuidance: type: number description: >- A number between 1 and 2. This number influences how closely the generated speech adheres to the input text. Use lower values to create more fluid speech, but with a higher chance of deviating from the input text. Higher numbers will make the generated speech more accurate to the input text, ensuring that the words spoken align closely with the provided text. minimum: 1 maximum: 2 example: null model: type: string description: Playht voice model/engine to use. enum: - PlayHT2.0 - PlayHT2.0-turbo - Play3.0-mini - PlayDialog language: type: string description: The language to use for the speech. enum: - afrikaans - albanian - amharic - arabic - bengali - bulgarian - catalan - croatian - czech - danish - dutch - english - french - galician - german - greek - hebrew - hindi - hungarian - indonesian - italian - japanese - korean - malay - mandarin - polish - portuguese - russian - serbian - spanish - swedish - tagalog - thai - turkish - ukrainian - urdu - xhosa chunkPlan: description: >- This is the plan for chunking the model output before it is sent to the voice provider. allOf: - $ref: '#/components/schemas/ChunkPlan' fallbackPlan: description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. allOf: - $ref: '#/components/schemas/FallbackPlan' required: - provider - voiceId RimeAIVoice: type: object properties: cachingEnabled: type: boolean description: This is the flag to toggle voice caching for the assistant. example: true default: true provider: type: string description: This is the voice provider that will be used. enum: - rime-ai voiceId: description: This is the provider-specific ID that will be used. oneOf: - type: string enum: - abbie - allison - ally - alona - amber - ana - antoine - armon - brenda - brittany - carol - colin - courtney - elena - elliot - eva - geoff - gerald - hank - helen - hera - jen - joe - joy - juan - kendra - kendrick - kenneth - kevin - kris - linda - madison - marge - marina - marissa - marta - maya - nicholas - nyles - phil - reba - rex - rick - ritu - rob - rodney - rohan - rosco - samantha - sandy - selena - seth - sharon - stan - tamra - tanya - tibur - tj - tyler - viv - yadira - marsh - bayou - creek - brook - flower - spore - glacier - gulch - alpine - cove - lagoon - tundra - steppe - mesa - grove - rainforest - moraine - wildflower - peak - boulder - gypsum - zest - luna - celeste - orion - ursa - astra - esther - estelle - andromeda title: Preset Voice Options - type: string title: RimeAI Voice ID model: type: string description: >- This is the model that will be used. Defaults to 'mistv2' when not specified. enum: - mist - mistv2 - arcana example: mistv2 speed: type: number description: This is the speed multiplier that will be used. minimum: 0.1 example: null pauseBetweenBrackets: type: boolean description: >- This is a flag that controls whether to add slight pauses using angle brackets. Example: "Hi. <200> I'd love to have a conversation with you." adds a 200ms pause between the first and second sentences. example: false phonemizeBetweenBrackets: type: boolean description: >- This is a flag that controls whether text inside brackets should be phonemized (converted to phonetic pronunciation) - Example: "{h'El.o} World" will pronounce "Hello" as expected. example: false reduceLatency: type: boolean description: >- This is a flag that controls whether to optimize for reduced latency in streaming. https://docs.rime.ai/api-reference/endpoint/websockets#param-reduce-latency example: false inlineSpeedAlpha: type: string description: >- This is a string that allows inline speed control using alpha notation. https://docs.rime.ai/api-reference/endpoint/websockets#param-inline-speed-alpha example: null chunkPlan: description: >- This is the plan for chunking the model output before it is sent to the voice provider. allOf: - $ref: '#/components/schemas/ChunkPlan' fallbackPlan: description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. allOf: - $ref: '#/components/schemas/FallbackPlan' required: - provider - voiceId SmallestAIVoice: type: object properties: cachingEnabled: type: boolean description: This is the flag to toggle voice caching for the assistant. example: true default: true provider: type: string description: This is the voice provider that will be used. enum: - smallest-ai voiceId: description: This is the provider-specific ID that will be used. oneOf: - type: string enum: - emily - jasmine - arman - james - mithali - aravind - raj - diya - raman - ananya - isha - william - aarav - monika - niharika - deepika - raghav - kajal - radhika - mansi - nisha - saurabh - pooja - saina - sanya title: Preset Voice Options - type: string title: Smallest AI Voice ID model: type: string description: >- Smallest AI voice model to use. Defaults to 'lightning' when not specified. enum: - lightning speed: type: number description: This is the speed multiplier that will be used. example: null chunkPlan: description: >- This is the plan for chunking the model output before it is sent to the voice provider. allOf: - $ref: '#/components/schemas/ChunkPlan' fallbackPlan: description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. allOf: - $ref: '#/components/schemas/FallbackPlan' required: - provider - voiceId TavusVoice: type: object properties: cachingEnabled: type: boolean description: This is the flag to toggle voice caching for the assistant. example: true default: true provider: type: string description: This is the voice provider that will be used. enum: - tavus voiceId: description: This is the provider-specific ID that will be used. oneOf: - type: string enum: - r52da2535a title: Preset Voice Options - type: string title: Tavus Voice ID chunkPlan: description: >- This is the plan for chunking the model output before it is sent to the voice provider. allOf: - $ref: '#/components/schemas/ChunkPlan' personaId: type: string description: >- This is the unique identifier for the persona that the replica will use in the conversation. callbackUrl: type: string description: >- This is the url that will receive webhooks with updates regarding the conversation state. conversationName: type: string description: This is the name for the conversation. conversationalContext: type: string description: >- This is the context that will be appended to any context provided in the persona, if one is provided. customGreeting: type: string description: >- This is the custom greeting that the replica will give once a participant joines the conversation. properties: description: These are optional properties used to customize the conversation. allOf: - $ref: '#/components/schemas/TavusConversationProperties' fallbackPlan: description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. allOf: - $ref: '#/components/schemas/FallbackPlan' required: - provider - voiceId cozmoxVoice: type: object properties: cachingEnabled: type: boolean description: This is the flag to toggle voice caching for the assistant. example: true default: true provider: type: string description: This is the voice provider that will be used. enum: - cozmox voiceId: type: string description: The voices provided by cozmox enum: - Elliot - Kylie - Rohan - Lily - Savannah - Hana - Neha - Cole - Harry - Paige - Spencer speed: type: number description: |- This is the speed multiplier that will be used. @default 1 minimum: 0.25 maximum: 2 default: 1 chunkPlan: description: >- This is the plan for chunking the model output before it is sent to the voice provider. allOf: - $ref: '#/components/schemas/ChunkPlan' fallbackPlan: description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. allOf: - $ref: '#/components/schemas/FallbackPlan' required: - provider - voiceId SesameVoice: type: object properties: cachingEnabled: type: boolean description: This is the flag to toggle voice caching for the assistant. example: true default: true provider: type: string description: This is the voice provider that will be used. enum: - sesame voiceId: type: string description: This is the provider-specific ID that will be used. title: >- Sesame Voice ID. This should be either a name (a built-in voice) or a UUID (a custom voice). model: type: string description: This is the model that will be used. enum: - csm-1b chunkPlan: description: >- This is the plan for chunking the model output before it is sent to the voice provider. allOf: - $ref: '#/components/schemas/ChunkPlan' fallbackPlan: description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. allOf: - $ref: '#/components/schemas/FallbackPlan' required: - provider - voiceId - model InworldVoice: type: object properties: cachingEnabled: type: boolean description: This is the flag to toggle voice caching for the assistant. example: true default: true provider: type: string description: This is the voice provider that will be used. enum: - inworld voiceId: type: string description: >- Available voices by language: • en: Alex, Ashley, Craig, Deborah, Dennis, Edward, Elizabeth, Hades, Julia, Pixie, Mark, Olivia, Priya, Ronald, Sarah, Shaun, Theodore, Timothy, Wendy, Dominus • zh: Yichen, Xiaoyin, Xinyi, Jing • nl: Erik, Katrien, Lennart, Lore • fr: Alain, Hélène, Mathieu, Étienne • de: Johanna, Josef • it: Gianni, Orietta • ja: Asuka, Satoshi • ko: Hyunwoo, Minji, Seojun, Yoona • pl: Szymon, Wojciech • pt: Heitor, Maitê • es: Diego, Lupita, Miguel, Rafael maxLength: 120 title: Inworld Voice ID enum: - Alex - Ashley - Craig - Deborah - Dennis - Edward - Elizabeth - Hades - Julia - Pixie - Mark - Olivia - Priya - Ronald - Sarah - Shaun - Theodore - Timothy - Wendy - Dominus - Yichen - Xiaoyin - Xinyi - Jing - Erik - Katrien - Lennart - Lore - Alain - Hélène - Mathieu - Étienne - Johanna - Josef - Gianni - Orietta - Asuka - Satoshi - Hyunwoo - Minji - Seojun - Yoona - Szymon - Wojciech - Heitor - Maitê - Diego - Lupita - Miguel - Rafael example: Alex model: type: string description: This is the model that will be used. enum: - inworld-tts-1 default: inworld-tts-1 languageCode: type: string description: Language code for Inworld TTS synthesis default: en enum: - en - zh - ko - nl - fr - es - ja - de - it - pl - pt chunkPlan: description: >- This is the plan for chunking the model output before it is sent to the voice provider. allOf: - $ref: '#/components/schemas/ChunkPlan' fallbackPlan: description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. allOf: - $ref: '#/components/schemas/FallbackPlan' required: - provider - voiceId GoogleVoicemailDetectionPlan: type: object properties: beepMaxAwaitSeconds: type: number description: >- This is the maximum duration from the start of the call that we will wait for a voicemail beep, before speaking our message - If we detect a voicemail beep before this, we will speak the message at that point. - Setting too low a value means that the bot will start speaking its voicemail message too early. If it does so before the actual beep, it will get cut off. You should definitely tune this to your use case. @default 30 @min 0 @max 60 minimum: 0 maximum: 30 default: 30 provider: type: string description: This is the provider to use for voicemail detection. enum: - google backoffPlan: description: This is the backoff plan for the voicemail detection. allOf: - $ref: '#/components/schemas/VoicemailDetectionBackoffPlan' required: - provider OpenAIVoicemailDetectionPlan: type: object properties: beepMaxAwaitSeconds: type: number description: >- This is the maximum duration from the start of the call that we will wait for a voicemail beep, before speaking our message - If we detect a voicemail beep before this, we will speak the message at that point. - Setting too low a value means that the bot will start speaking its voicemail message too early. If it does so before the actual beep, it will get cut off. You should definitely tune this to your use case. @default 30 @min 0 @max 60 minimum: 0 maximum: 30 default: 30 provider: type: string description: This is the provider to use for voicemail detection. enum: - openai backoffPlan: description: This is the backoff plan for the voicemail detection. allOf: - $ref: '#/components/schemas/VoicemailDetectionBackoffPlan' required: - provider TwilioVoicemailDetectionPlan: type: object properties: provider: type: string description: This is the provider to use for voicemail detection. enum: - twilio voicemailDetectionTypes: type: array description: >- These are the AMD messages from Twilio that are considered as voicemail. Default is ['machine_end_beep', 'machine_end_silence']. @default {Array} ['machine_end_beep', 'machine_end_silence'] enum: - machine_start - human - fax - unknown - machine_end_beep - machine_end_silence - machine_end_other example: - machine_end_beep - machine_end_silence items: type: string enum: - machine_start - human - fax - unknown - machine_end_beep - machine_end_silence - machine_end_other enabled: type: boolean description: >- This sets whether the assistant should detect voicemail. Defaults to true. @default true machineDetectionTimeout: type: number description: >- The number of seconds that Twilio should attempt to perform answering machine detection before timing out and returning AnsweredBy as unknown. Default is 30 seconds. Increasing this value will provide the engine more time to make a determination. This can be useful when DetectMessageEnd is provided in the MachineDetection parameter and there is an expectation of long answering machine greetings that can exceed 30 seconds. Decreasing this value will reduce the amount of time the engine has to make a determination. This can be particularly useful when the Enable option is provided in the MachineDetection parameter and you want to limit the time for initial detection. Check the [Twilio docs](https://www.twilio.com/docs/voice/answering-machine-detection#optional-api-tuning-parameters) for more info. @default 30 minimum: 3 maximum: 59 machineDetectionSpeechThreshold: type: number description: >- The number of milliseconds that is used as the measuring stick for the length of the speech activity. Durations lower than this value will be interpreted as a human, longer as a machine. Default is 2400 milliseconds. Increasing this value will reduce the chance of a False Machine (detected machine, actually human) for a long human greeting (e.g., a business greeting) but increase the time it takes to detect a machine. Decreasing this value will reduce the chances of a False Human (detected human, actually machine) for short voicemail greetings. The value of this parameter may need to be reduced by more than 1000ms to detect very short voicemail greetings. A reduction of that significance can result in increased False Machine detections. Adjusting the MachineDetectionSpeechEndThreshold is likely the better approach for short voicemails. Decreasing MachineDetectionSpeechThreshold will also reduce the time it takes to detect a machine. Check the [Twilio docs](https://www.twilio.com/docs/voice/answering-machine-detection#optional-api-tuning-parameters) for more info. @default 2400 minimum: 1000 maximum: 6000 machineDetectionSpeechEndThreshold: type: number description: >- The number of milliseconds of silence after speech activity at which point the speech activity is considered complete. Default is 1200 milliseconds. Increasing this value will typically be used to better address the short voicemail greeting scenarios. For short voicemails, there is typically 1000-2000ms of audio followed by 1200-2400ms of silence and then additional audio before the beep. Increasing the MachineDetectionSpeechEndThreshold to ~2500ms will treat the 1200-2400ms of silence as a gap in the greeting but not the end of the greeting and will result in a machine detection. The downsides of such a change include: - Increasing the delay for human detection by the amount you increase this parameter, e.g., a change of 1200ms to 2500ms increases human detection delay by 1300ms. - Cases where a human has two utterances separated by a period of silence (e.g. a "Hello", then 2000ms of silence, and another "Hello") may be interpreted as a machine. Decreasing this value will result in faster human detection. The consequence is that it can lead to increased False Human (detected human, actually machine) detections because a silence gap in a voicemail greeting (not necessarily just in short voicemail scenarios) can be incorrectly interpreted as the end of speech. Check the [Twilio docs](https://www.twilio.com/docs/voice/answering-machine-detection#optional-api-tuning-parameters) for more info. @default 1200 minimum: 500 maximum: 5000 machineDetectionSilenceTimeout: type: number description: >- The number of milliseconds of initial silence after which an unknown AnsweredBy result will be returned. Default is 5000 milliseconds. Increasing this value will result in waiting for a longer period of initial silence before returning an 'unknown' AMD result. Decreasing this value will result in waiting for a shorter period of initial silence before returning an 'unknown' AMD result. Check the [Twilio docs](https://www.twilio.com/docs/voice/answering-machine-detection#optional-api-tuning-parameters) for more info. @default 5000 minimum: 2000 maximum: 10000 required: - provider cozmoxVoicemailDetectionPlan: type: object properties: beepMaxAwaitSeconds: type: number description: >- This is the maximum duration from the start of the call that we will wait for a voicemail beep, before speaking our message - If we detect a voicemail beep before this, we will speak the message at that point. - Setting too low a value means that the bot will start speaking its voicemail message too early. If it does so before the actual beep, it will get cut off. You should definitely tune this to your use case. @default 30 @min 0 @max 60 minimum: 0 maximum: 30 default: 30 provider: type: string description: This is the provider to use for voicemail detection. enum: - cozmox backoffPlan: description: This is the backoff plan for the voicemail detection. allOf: - $ref: '#/components/schemas/VoicemailDetectionBackoffPlan' required: - provider TransportConfigurationTwilio: type: object properties: provider: type: string enum: - twilio timeout: type: number description: >- The integer number of seconds that we should allow the phone to ring before assuming there is no answer. The default is `60` seconds and the maximum is `600` seconds. For some call flows, we will add a 5-second buffer to the timeout value you provide. For this reason, a timeout value of 10 seconds could result in an actual timeout closer to 15 seconds. You can set this to a short time, such as `15` seconds, to hang up before reaching an answering machine or voicemail. @default 60 minimum: 1 maximum: 600 example: 60 record: type: boolean description: |- Whether to record the call. Can be `true` to record the phone call, or `false` to not. The default is `false`. @default false example: false recordingChannels: type: string description: >- The number of channels in the final recording. Can be: `mono` or `dual`. The default is `mono`. `mono` records both legs of the call in a single channel of the recording file. `dual` records each leg to a separate channel of the recording file. The first channel of a dual-channel recording contains the parent call and the second channel contains the child call. @default 'mono' enum: - mono - dual example: mono required: - provider LangfuseObservabilityPlan: type: object properties: provider: type: string enum: - langfuse tags: description: >- This is an array of tags to be added to the Langfuse trace. Tags allow you to categorize and filter traces. https://langfuse.com/docs/tracing-features/tags type: array items: type: string metadata: type: object description: >- This is a JSON object that will be added to the Langfuse trace. Traces can be enriched with metadata to better understand your users, application, and experiments. https://langfuse.com/docs/tracing-features/metadata By default it includes the call metadata, assistant metadata, and assistant overrides. required: - provider - tags CreateAnthropicCredentialDTO: type: object properties: provider: type: string enum: - anthropic apiKey: type: string maxLength: 10000 description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - apiKey CreateAnyscaleCredentialDTO: type: object properties: provider: type: string enum: - anyscale apiKey: type: string maxLength: 10000 description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - apiKey CreateAssemblyAICredentialDTO: type: object properties: provider: type: string enum: - assembly-ai apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - apiKey CreateAzureCredentialDTO: type: object properties: provider: type: string enum: - azure service: type: string description: This is the service being used in Azure. enum: - speech - blob_storage default: speech region: type: string description: This is the region of the Azure resource. enum: - australia - canadaeast - canadacentral - eastus2 - eastus - france - india - japaneast - japanwest - uaenorth - northcentralus - norway - southcentralus - swedencentral - switzerland - uk - westus - westus3 apiKey: type: string maxLength: 10000 description: This is not returned in the API. fallbackIndex: type: number minimum: 1 description: >- This is the order in which this storage provider is tried during upload retries. Lower numbers are tried first in increasing order. bucketPlan: description: >- This is the bucket plan that can be provided to store call artifacts in Azure Blob Storage. allOf: - $ref: '#/components/schemas/AzureBlobStorageBucketPlan' name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - service CreateAzureOpenAICredentialDTO: type: object properties: provider: type: string enum: - azure-openai region: type: string enum: - australia - canadaeast - canadacentral - eastus2 - eastus - france - india - japaneast - japanwest - uaenorth - northcentralus - norway - southcentralus - swedencentral - switzerland - uk - westus - westus3 models: type: array enum: - gpt-4.1-2025-04-14 - gpt-4.1-mini-2025-04-14 - gpt-4.1-nano-2025-04-14 - gpt-4o-2024-11-20 - gpt-4o-2024-08-06 - gpt-4o-2024-05-13 - gpt-4o-mini-2024-07-18 - gpt-4-turbo-2024-04-09 - gpt-4-0125-preview - gpt-4-1106-preview - gpt-4-0613 - gpt-35-turbo-0125 - gpt-35-turbo-1106 example: - gpt-4-0125-preview - gpt-4-0613 items: type: string enum: - gpt-4.1-2025-04-14 - gpt-4.1-mini-2025-04-14 - gpt-4.1-nano-2025-04-14 - gpt-4o-2024-11-20 - gpt-4o-2024-08-06 - gpt-4o-2024-05-13 - gpt-4o-mini-2024-07-18 - gpt-4-turbo-2024-04-09 - gpt-4-0125-preview - gpt-4-1106-preview - gpt-4-0613 - gpt-35-turbo-0125 - gpt-35-turbo-1106 openAIKey: type: string maxLength: 10000 description: This is not returned in the API. ocpApimSubscriptionKey: type: string description: This is not returned in the API. openAIEndpoint: type: string maxLength: 10000 name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - region - models - openAIKey - openAIEndpoint CreateByoSipTrunkCredentialDTO: type: object properties: provider: type: string description: >- This can be used to bring your own SIP trunks or to connect to a Carrier. enum: - byo-sip-trunk gateways: description: This is the list of SIP trunk's gateways. type: array items: $ref: '#/components/schemas/SipTrunkGateway' outboundAuthenticationPlan: description: >- This can be used to configure the outbound authentication if required by the SIP trunk. allOf: - $ref: '#/components/schemas/SipTrunkOutboundAuthenticationPlan' outboundLeadingPlusEnabled: type: boolean description: >- This ensures the outbound origination attempts have a leading plus. Defaults to false to match conventional telecom behavior. Usage: - Vonage/Twilio requires leading plus for all outbound calls. Set this to true. @default false techPrefix: type: string description: >- This can be used to configure the tech prefix on outbound calls. This is an advanced property. maxLength: 10000 sipDiversionHeader: type: string description: >- This can be used to enable the SIP diversion header for authenticating the calling number if the SIP trunk supports it. This is an advanced property. maxLength: 10000 sbcConfiguration: description: >- This is an advanced configuration for enterprise deployments. This uses the onprem SBC to trunk into the SIP trunk's `gateways`, rather than the managed SBC provided by cozmox. allOf: - $ref: '#/components/schemas/SbcConfiguration' name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - gateways CreateCartesiaCredentialDTO: type: object properties: provider: type: string enum: - cartesia apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - apiKey CreateCerebrasCredentialDTO: type: object properties: provider: type: string enum: - cerebras apiKey: type: string maxLength: 10000 description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - apiKey CreateCloudflareCredentialDTO: type: object properties: provider: type: string enum: - cloudflare description: Credential provider. Only allowed value is cloudflare accountId: type: string description: Cloudflare Account Id. apiKey: type: string description: Cloudflare API Key / Token. accountEmail: type: string description: Cloudflare Account Email. fallbackIndex: type: number minimum: 1 description: >- This is the order in which this storage provider is tried during upload retries. Lower numbers are tried first in increasing order. bucketPlan: description: >- This is the bucket plan that can be provided to store call artifacts in R2 allOf: - $ref: '#/components/schemas/CloudflareR2BucketPlan' name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider CreateCustomLLMCredentialDTO: type: object properties: provider: type: string enum: - custom-llm apiKey: type: string maxLength: 10000 description: This is not returned in the API. authenticationPlan: description: >- This is the authentication plan. Currently supports OAuth2 RFC 6749. To use Bearer authentication, use apiKey allOf: - $ref: '#/components/schemas/OAuth2AuthenticationPlan' name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - apiKey CreateDeepgramCredentialDTO: type: object properties: provider: type: string enum: - deepgram apiKey: type: string description: This is not returned in the API. apiUrl: type: string description: >- This can be used to point to an onprem Deepgram instance. Defaults to api.deepgram.com. name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - apiKey CreateDeepInfraCredentialDTO: type: object properties: provider: type: string enum: - deepinfra apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - apiKey CreateDeepSeekCredentialDTO: type: object properties: provider: type: string enum: - deep-seek apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - apiKey CreateElevenLabsCredentialDTO: type: object properties: provider: type: string enum: - 11labs apiKey: type: string maxLength: 10000 description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - apiKey CreateGcpCredentialDTO: type: object properties: provider: type: string enum: - gcp fallbackIndex: type: number minimum: 1 description: >- This is the order in which this storage provider is tried during upload retries. Lower numbers are tried first in increasing order. gcpKey: description: >- This is the GCP key. This is the JSON that can be generated in the Google Cloud Console at https://console.cloud.google.com/iam-admin/serviceaccounts/details//keys. The schema is identical to the JSON that GCP outputs. allOf: - $ref: '#/components/schemas/GcpKey' region: type: string description: This is the region of the GCP resource. maxLength: 40 bucketPlan: $ref: '#/components/schemas/BucketPlan' name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - gcpKey CreateGladiaCredentialDTO: type: object properties: provider: type: string enum: - gladia apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - apiKey CreateGoHighLevelCredentialDTO: type: object properties: provider: type: string enum: - gohighlevel apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - apiKey CreateGoogleCredentialDTO: type: object properties: provider: type: string description: >- This is the key for Gemini in Google AI Studio. Get it from here: https://aistudio.google.com/app/apikey enum: - google apiKey: type: string maxLength: 10000 description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - apiKey CreateGroqCredentialDTO: type: object properties: provider: type: string enum: - groq apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - apiKey CreateHumeCredentialDTO: type: object properties: provider: type: string enum: - hume apiKey: type: string maxLength: 10000 description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - apiKey CreateInflectionAICredentialDTO: type: object properties: provider: type: string description: >- This is the api key for Pi in InflectionAI's console. Get it from here: https://developers.inflection.ai/keys, billing will need to be setup enum: - inflection-ai apiKey: type: string maxLength: 10000 description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - apiKey CreateLangfuseCredentialDTO: type: object properties: provider: type: string enum: - langfuse publicKey: type: string description: 'The public key for Langfuse project. Eg: pk-lf-...' apiKey: type: string description: >- The secret key for Langfuse project. Eg: sk-lf-... .This is not returned in the API. apiUrl: type: string description: 'The host URL for Langfuse project. Eg: https://cloud.langfuse.com' name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - publicKey - apiKey - apiUrl CreateLmntCredentialDTO: type: object properties: provider: type: string enum: - lmnt apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - apiKey CreateMakeCredentialDTO: type: object properties: provider: type: string enum: - make teamId: type: string description: Team ID region: type: string description: 'Region of your application. For example: eu1, eu2, us1, us2' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - teamId - region - apiKey CreateMistralCredentialDTO: type: object properties: provider: type: string enum: - mistral apiKey: type: string maxLength: 100 description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - apiKey CreateNeuphonicCredentialDTO: type: object properties: provider: type: string enum: - neuphonic apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - apiKey CreateOpenAICredentialDTO: type: object properties: provider: type: string enum: - openai apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - apiKey CreateOpenRouterCredentialDTO: type: object properties: provider: type: string enum: - openrouter apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - apiKey CreatePerplexityAICredentialDTO: type: object properties: provider: type: string enum: - perplexity-ai apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - apiKey CreatePlayHTCredentialDTO: type: object properties: provider: type: string enum: - playht apiKey: type: string description: This is not returned in the API. userId: type: string name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - apiKey - userId CreateRimeAICredentialDTO: type: object properties: provider: type: string enum: - rime-ai apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - apiKey CreateRunpodCredentialDTO: type: object properties: provider: type: string enum: - runpod apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - apiKey CreateS3CredentialDTO: type: object properties: provider: type: string enum: - s3 description: Credential provider. Only allowed value is s3 awsAccessKeyId: type: string description: AWS access key ID. awsSecretAccessKey: type: string description: AWS access key secret. This is not returned in the API. region: type: string description: AWS region in which the S3 bucket is located. s3BucketName: type: string description: AWS S3 bucket name. s3PathPrefix: type: string description: The path prefix for the uploaded recording. Ex. "recordings/" fallbackIndex: type: number minimum: 1 description: >- This is the order in which this storage provider is tried during upload retries. Lower numbers are tried first in increasing order. name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - awsAccessKeyId - awsSecretAccessKey - region - s3BucketName - s3PathPrefix CreateSmallestAICredentialDTO: type: object properties: provider: type: string enum: - smallest-ai apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - apiKey CreateSpeechmaticsCredentialDTO: type: object properties: provider: type: string enum: - speechmatics apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - apiKey CreateSupabaseCredentialDTO: type: object properties: provider: type: string enum: - supabase description: This is for supabase storage. fallbackIndex: type: number minimum: 1 description: >- This is the order in which this storage provider is tried during upload retries. Lower numbers are tried first in increasing order. bucketPlan: $ref: '#/components/schemas/SupabaseBucketPlan' name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider CreateTavusCredentialDTO: type: object properties: provider: type: string enum: - tavus apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - apiKey CreateTogetherAICredentialDTO: type: object properties: provider: type: string enum: - together-ai apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - apiKey CreateTrieveCredentialDTO: type: object properties: provider: type: string enum: - trieve apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - apiKey CreateTwilioCredentialDTO: type: object properties: provider: type: string enum: - twilio authToken: type: string description: This is not returned in the API. apiKey: type: string description: This is not returned in the API. apiSecret: type: string description: This is not returned in the API. accountSid: type: string name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - accountSid CreateVonageCredentialDTO: type: object properties: provider: type: string enum: - vonage apiSecret: type: string description: This is not returned in the API. apiKey: type: string name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - apiSecret - apiKey CreateWebhookCredentialDTO: type: object properties: provider: type: string enum: - webhook authenticationPlan: description: >- This is the authentication plan. Supports OAuth2 RFC 6749 and HMAC signing. oneOf: - $ref: '#/components/schemas/OAuth2AuthenticationPlan' - $ref: '#/components/schemas/HMACAuthenticationPlan' discriminator: propertyName: type mapping: oauth2: '#/components/schemas/OAuth2AuthenticationPlan' hmac: '#/components/schemas/HMACAuthenticationPlan' name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - authenticationPlan CreateXAiCredentialDTO: type: object properties: provider: type: string description: >- This is the api key for Grok in XAi's console. Get it from here: https://console.x.ai enum: - xai apiKey: type: string maxLength: 10000 description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - apiKey CreateGoogleCalendarOAuth2ClientCredentialDTO: type: object properties: provider: type: string enum: - google.calendar.oauth2-client name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider CreateGoogleCalendarOAuth2AuthorizationCredentialDTO: type: object properties: provider: type: string enum: - google.calendar.oauth2-authorization authorizationId: type: string description: The authorization ID for the OAuth2 authorization name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - authorizationId CreateGoogleSheetsOAuth2AuthorizationCredentialDTO: type: object properties: provider: type: string enum: - google.sheets.oauth2-authorization authorizationId: type: string description: The authorization ID for the OAuth2 authorization name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - authorizationId CreateSlackOAuth2AuthorizationCredentialDTO: type: object properties: provider: type: string enum: - slack.oauth2-authorization authorizationId: type: string description: The authorization ID for the OAuth2 authorization name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - authorizationId CreateGoHighLevelMCPCredentialDTO: type: object properties: provider: type: string enum: - ghl.oauth2-authorization authenticationSession: description: This is the authentication session for the credential. allOf: - $ref: '#/components/schemas/Oauth2AuthenticationSession' name: type: string description: This is the name of credential. This is just for your reference. minLength: 1 maxLength: 40 required: - provider - authenticationSession AssistantHookCallEnding: type: object properties: 'on': type: string description: This is the event that triggers this hook enum: - call.ending maxLength: 1000 do: type: array description: This is the set of actions to perform when the hook triggers items: oneOf: - $ref: '#/components/schemas/TransferAssistantHookAction' title: TransferAssistantHookAction - $ref: '#/components/schemas/FunctionCallAssistantHookAction' title: FunctionCallAssistantHookAction filters: description: This is the set of filters that must match for the hook to trigger type: array items: $ref: '#/components/schemas/AssistantHookFilter' required: - 'on' - do AssistantHookAssistantSpeechInterrupted: type: object properties: 'on': type: string description: This is the event that triggers this hook enum: - assistant.speech.interrupted maxLength: 1000 do: type: array description: This is the set of actions to perform when the hook triggers items: oneOf: - $ref: '#/components/schemas/TransferAssistantHookAction' title: TransferAssistantHookAction - $ref: '#/components/schemas/FunctionCallAssistantHookAction' title: FunctionCallAssistantHookAction - $ref: '#/components/schemas/SayAssistantHookAction' title: SayAssistantHookAction required: - 'on' - do AssistantHookCustomerSpeechInterrupted: type: object properties: 'on': type: string description: This is the event that triggers this hook enum: - customer.speech.interrupted maxLength: 1000 do: type: array description: This is the set of actions to perform when the hook triggers items: oneOf: - $ref: '#/components/schemas/TransferAssistantHookAction' title: TransferAssistantHookAction - $ref: '#/components/schemas/FunctionCallAssistantHookAction' title: FunctionCallAssistantHookAction - $ref: '#/components/schemas/SayAssistantHookAction' title: SayAssistantHookAction required: - 'on' - do CompliancePlan: type: object properties: hipaaEnabled: type: boolean description: >- When this is enabled, no logs, recordings, or transcriptions will be stored. At the end of the call, you will still receive an end-of-call-report message to store on your server. Defaults to false. example: hipaaEnabled: false pciEnabled: type: boolean description: >- When this is enabled, the user will be restricted to use PCI-compliant providers, and no logs or transcripts are stored. At the end of the call, you will receive an end-of-call-report message to store on your server. Defaults to false. example: pciEnabled: false BackgroundSpeechDenoisingPlan: type: object properties: smartDenoisingPlan: description: Whether smart denoising using Krisp is enabled. allOf: - $ref: '#/components/schemas/SmartDenoisingPlan' fourierDenoisingPlan: description: >- Whether Fourier denoising is enabled. Note that this is experimental and may not work as expected. This can be combined with smart denoising, and will be run afterwards. allOf: - $ref: '#/components/schemas/FourierDenoisingPlan' AnalysisPlan: type: object properties: minMessagesThreshold: type: number description: >- The minimum number of messages required to run the analysis plan. If the number of messages is less than this, analysis will be skipped. @default 2 minimum: 0 summaryPlan: description: >- This is the plan for generating the summary of the call. This outputs to `call.analysis.summary`. allOf: - $ref: '#/components/schemas/SummaryPlan' structuredDataPlan: description: >- This is the plan for generating the structured data from the call. This outputs to `call.analysis.structuredData`. allOf: - $ref: '#/components/schemas/StructuredDataPlan' structuredDataMultiPlan: description: >- This is an array of structured data plan catalogs. Each entry includes a `key` and a `plan` for generating the structured data from the call. This outputs to `call.analysis.structuredDataMulti`. type: array items: $ref: '#/components/schemas/StructuredDataMultiPlan' successEvaluationPlan: description: >- This is the plan for generating the success evaluation of the call. This outputs to `call.analysis.successEvaluation`. allOf: - $ref: '#/components/schemas/SuccessEvaluationPlan' ArtifactPlan: type: object properties: recordingEnabled: type: boolean description: >- This determines whether assistant's calls are recorded. Defaults to true. Usage: - If you don't want to record the calls, set this to false. - If you want to record the calls when `assistant.hipaaEnabled` (deprecated) or `assistant.compliancePlan.hipaaEnabled` explicity set this to true and make sure to provide S3 or GCP credentials on the Provider Credentials page in the Dashboard. You can find the recording at `call.artifact.recordingUrl` and `call.artifact.stereoRecordingUrl` after the call is ended. @default true example: true recordingFormat: type: string description: |- This determines the format of the recording. Defaults to `wav;l16`. @default 'wav;l16' enum: - wav;l16 - mp3 videoRecordingEnabled: type: boolean description: >- This determines whether the video is recorded during the call. Defaults to false. Only relevant for `webCall` type. You can find the video recording at `call.artifact.videoRecordingUrl` after the call is ended. @default false example: false pcapEnabled: type: boolean description: >- This determines whether the SIP packet capture is enabled. Defaults to true. Only relevant for `phone` type calls where phone number's provider is `cozmox` or `byo-phone-number`. You can find the packet capture at `call.artifact.pcapUrl` after the call is ended. @default true example: true pcapS3PathPrefix: type: string description: >- This is the path where the SIP packet capture will be uploaded. This is only used if you have provided S3 or GCP credentials on the Provider Credentials page in the Dashboard. If credential.s3PathPrefix or credential.bucketPlan.path is set, this will append to it. Usage: - If you want to upload the packet capture to a specific path, set this to the path. Example: `/my-assistant-captures`. - If you want to upload the packet capture to the root of the bucket, set this to `/`. @default '/' example: /pcaps transcriptPlan: description: >- This is the plan for `call.artifact.transcript`. To disable, set `transcriptPlan.enabled` to false. allOf: - $ref: '#/components/schemas/TranscriptPlan' recordingPath: type: string description: >- This is the path where the recording will be uploaded. This is only used if you have provided S3 or GCP credentials on the Provider Credentials page in the Dashboard. If credential.s3PathPrefix or credential.bucketPlan.path is set, this will append to it. Usage: - If you want to upload the recording to a specific path, set this to the path. Example: `/my-assistant-recordings`. - If you want to upload the recording to the root of the bucket, set this to `/`. @default '/' MessagePlan: type: object properties: idleMessages: description: >- This are the messages that the assistant will speak when the user hasn't responded for `idleTimeoutSeconds`. Each time the timeout is triggered, a random message will be chosen from this array. Usage: - If user gets distracted and doesn't respond for a while, this can be used to grab their attention. - If the transcriber doesn't pick up what the user said, this can be used to ask the user to repeat themselves. (From the perspective of the assistant, the conversation is idle since it didn't "hear" any user messages.) @default null (no idle message is spoken) type: array items: type: string maxLength: 1000 idleMessageMaxSpokenCount: type: number description: >- This determines the maximum number of times `idleMessages` can be spoken during the call. @default 3 minimum: 1 maximum: 10 idleMessageResetCountOnUserSpeechEnabled: type: boolean description: >- This determines whether the idle message count is reset whenever the user speaks. @default false idleTimeoutSeconds: type: number description: >- This is the timeout in seconds before a message from `idleMessages` is spoken. The clock starts when the assistant finishes speaking and remains active until the user speaks. @default 10 minimum: 5 maximum: 60 silenceTimeoutMessage: type: string description: >- This is the message that the assistant will say if the call ends due to silence. If unspecified, it will hang up without saying anything. maxLength: 1000 StartSpeakingPlan: type: object properties: waitSeconds: type: number description: >- This is how long assistant waits before speaking. Defaults to 0.4. This is the minimum it will wait but if there is latency is the pipeline, this minimum will be exceeded. This is intended as a stopgap in case the pipeline is moving too fast. Example: - If model generates tokens and voice generates bytes within 100ms, the pipeline still waits 300ms before outputting speech. Usage: - If the customer is taking long pauses, set this to a higher value. - If the assistant is accidentally jumping in too much, set this to a higher value. @default 0.4 minimum: 0 maximum: 5 example: 0.4 smartEndpointingEnabled: example: false deprecated: true oneOf: - type: boolean - type: string enum: - livekit smartEndpointingPlan: description: >- This is the plan for smart endpointing. Pick between cozmox smart endpointing or LiveKit smart endpointing (or nothing). We strongly recommend using livekit endpointing when working in English. LiveKit endpointing is not supported in other languages, yet. If this is set, it will override and take precedence over `transcriptionEndpointingPlan`. This plan will still be overridden by any matching `customEndpointingRules`. oneOf: - $ref: '#/components/schemas/cozmoxSmartEndpointingPlan' title: cozmox - $ref: '#/components/schemas/LivekitSmartEndpointingPlan' title: Livekit - $ref: '#/components/schemas/CustomEndpointingModelSmartEndpointingPlan' title: Custom Endpointing Model customEndpointingRules: type: array description: >- These are the custom endpointing rules to set an endpointing timeout based on a regex on the customer's speech or the assistant's last message. Usage: - If you have yes/no questions like "are you interested in a loan?", you can set a shorter timeout. - If you have questions where the customer may pause to look up information like "what's my account number?", you can set a longer timeout. - If you want to wait longer while customer is enumerating a list of numbers, you can set a longer timeout. These rules have the highest precedence and will override both `smartEndpointingPlan` and `transcriptionEndpointingPlan` when a rule is matched. The rules are evaluated in order and the first one that matches will be used. Order of precedence for endpointing: 1. customEndpointingRules (if any match) 2. smartEndpointingPlan (if set) 3. transcriptionEndpointingPlan @default [] items: oneOf: - $ref: '#/components/schemas/AssistantCustomEndpointingRule' title: Assistant - $ref: '#/components/schemas/CustomerCustomEndpointingRule' title: Customer - $ref: '#/components/schemas/BothCustomEndpointingRule' title: Both transcriptionEndpointingPlan: description: >- This determines how a customer speech is considered done (endpointing) using the transcription of customer's speech. Once an endpoint is triggered, the request is sent to `assistant.model`. Note: This plan is only used if `smartEndpointingPlan` is not set. If both are provided, `smartEndpointingPlan` takes precedence. This plan will also be overridden by any matching `customEndpointingRules`. allOf: - $ref: '#/components/schemas/TranscriptionEndpointingPlan' StopSpeakingPlan: type: object properties: numWords: type: number description: >- This is the number of words that the customer has to say before the assistant will stop talking. Words like "stop", "actually", "no", etc. will always interrupt immediately regardless of this value. Words like "okay", "yeah", "right" will never interrupt. When set to 0, `voiceSeconds` is used in addition to the transcriptions to determine the customer has started speaking. Defaults to 0. @default 0 minimum: 0 maximum: 10 example: 0 voiceSeconds: type: number description: >- This is the seconds customer has to speak before the assistant stops talking. This uses the VAD (Voice Activity Detection) spike to determine if the customer has started speaking. Considerations: - A lower value might be more responsive but could potentially pick up non-speech sounds. - A higher value reduces false positives but might slightly delay the detection of speech onset. This is only used if `numWords` is set to 0. Defaults to 0.2 @default 0.2 minimum: 0 maximum: 0.5 example: 0.2 backoffSeconds: type: number description: >- This is the seconds to wait before the assistant will start talking again after being interrupted. Defaults to 1. @default 1 minimum: 0 maximum: 10 example: 1 acknowledgementPhrases: description: >- These are the phrases that will never interrupt the assistant, even if numWords threshold is met. These are typically acknowledgement or backchanneling phrases. example: - i understand - i see - i got it - i hear you - im listening - im with you - right - okay - ok - sure - alright - got it - understood - yeah - 'yes' - uh-huh - mm-hmm - gotcha - mhmm - ah - yeah okay - yeah sure default: - i understand - i see - i got it - i hear you - im listening - im with you - right - okay - ok - sure - alright - got it - understood - yeah - 'yes' - uh-huh - mm-hmm - gotcha - mhmm - ah - yeah okay - yeah sure type: array items: type: string maxLength: 240 interruptionPhrases: description: >- These are the phrases that will always interrupt the assistant immediately, regardless of numWords. These are typically phrases indicating disagreement or desire to stop. example: - stop - shut - up - enough - quiet - silence - but - dont - not - 'no' - hold - wait - cut - pause - nope - nah - nevermind - never - bad - actually default: - stop - shut - up - enough - quiet - silence - but - dont - not - 'no' - hold - wait - cut - pause - nope - nah - nevermind - never - bad - actually type: array items: type: string maxLength: 240 MonitorPlan: type: object properties: listenEnabled: type: boolean description: >- This determines whether the assistant's calls allow live listening. Defaults to true. Fetch `call.monitor.listenUrl` to get the live listening URL. @default true example: false listenAuthenticationEnabled: type: boolean description: >- This enables authentication on the `call.monitor.listenUrl`. If `listenAuthenticationEnabled` is `true`, the `call.monitor.listenUrl` will require an `Authorization: Bearer ` header. @default false example: false controlEnabled: type: boolean description: >- This determines whether the assistant's calls allow live control. Defaults to true. Fetch `call.monitor.controlUrl` to get the live control URL. To use, send any control message via a POST request to `call.monitor.controlUrl`. Here are the types of controls supported: https://docs.cozmox.ai/api-reference/messages/client-inbound-message @default true example: false controlAuthenticationEnabled: type: boolean description: >- This enables authentication on the `call.monitor.controlUrl`. If `controlAuthenticationEnabled` is `true`, the `call.monitor.controlUrl` will require an `Authorization: Bearer ` header. @default false example: false Server: type: object properties: timeoutSeconds: type: number description: >- This is the timeout in seconds for the request. Defaults to 20 seconds. @default 20 minimum: 1 maximum: 300 example: 20 url: type: string description: This is where the request will be sent. headers: type: object description: |- These are the headers to include in the request. Each key-value pair represents a header name and its value. backoffPlan: description: >- This is the backoff plan if the request fails. Defaults to undefined (the request will not be retried). @default undefined (the request will not be retried) allOf: - $ref: '#/components/schemas/BackoffPlan' KeypadInputPlan: type: object properties: enabled: type: boolean description: |- This keeps track of whether the user has enabled keypad input. By default, it is off. @default false timeoutSeconds: type: number description: >- This is the time in seconds to wait before processing the input. If the input is not received within this time, the input will be ignored. If set to "off", the input will be processed when the user enters a delimiter or immediately if no delimiter is used. @default 2 minimum: 0 maximum: 10 delimiters: type: string description: |- This is the delimiter(s) that will be used to process the input. Can be '#', '*', or an empty array. enum: - '#' - '*' - '' FallbackTranscriberPlan: type: object properties: transcribers: type: array items: oneOf: - $ref: '#/components/schemas/FallbackAssemblyAITranscriber' title: AssemblyAI - $ref: '#/components/schemas/FallbackAzureSpeechTranscriber' title: Azure - $ref: '#/components/schemas/FallbackCustomTranscriber' title: Custom - $ref: '#/components/schemas/FallbackDeepgramTranscriber' title: Deepgram - $ref: '#/components/schemas/FallbackElevenLabsTranscriber' title: ElevenLabs - $ref: '#/components/schemas/FallbackGladiaTranscriber' title: Gladia - $ref: '#/components/schemas/FallbackGoogleTranscriber' title: Google - $ref: '#/components/schemas/FallbackTalkscriberTranscriber' title: Talkscriber - $ref: '#/components/schemas/FallbackSpeechmaticsTranscriber' title: Speechmatics - $ref: '#/components/schemas/FallbackOpenAITranscriber' title: OpenAI - $ref: '#/components/schemas/FallbackCartesiaTranscriber' title: Cartesia required: - transcribers OpenAIMessage: type: object properties: content: type: string nullable: true maxLength: 100000000 role: type: string enum: - assistant - function - user - system - tool required: - content - role CreateApiRequestToolDTO: type: object properties: messages: type: array description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. items: oneOf: - $ref: '#/components/schemas/ToolMessageStart' title: ToolMessageStart - $ref: '#/components/schemas/ToolMessageComplete' title: ToolMessageComplete - $ref: '#/components/schemas/ToolMessageFailed' title: ToolMessageFailed - $ref: '#/components/schemas/ToolMessageDelayed' title: ToolMessageDelayed type: type: string enum: - apiRequest description: The type of tool. "apiRequest" for API request tool. method: type: string enum: - POST - GET timeoutSeconds: type: number description: >- This is the timeout in seconds for the request. Defaults to 20 seconds. @default 20 minimum: 1 maximum: 300 example: 20 name: type: string description: >- This is the name of the tool. This will be passed to the model. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 40. maxLength: 40 pattern: /^[a-zA-Z0-9_-]{1,40}$/ description: type: string description: >- This is the description of the tool. This will be passed to the model. maxLength: 1000 url: type: string description: This is where the request will be sent. body: description: This is the body of the request. allOf: - $ref: '#/components/schemas/JsonSchema' headers: description: These are the headers to send in the request. allOf: - $ref: '#/components/schemas/JsonSchema' backoffPlan: description: >- This is the backoff plan if the request fails. Defaults to undefined (the request will not be retried). @default undefined (the request will not be retried) allOf: - $ref: '#/components/schemas/BackoffPlan' variableExtractionPlan: description: >- This is the plan to extract variables from the tool's response. These will be accessible during the call and stored in `call.artifact.variableValues` after the call. Usage: 1. Use `aliases` to extract variables from the tool's response body. (Most common case) ```json { "aliases": [ { "key": "customerName", "value": "{{customer.name}}" }, { "key": "customerAge", "value": "{{customer.age}}" } ] } ``` The tool response body is made available to the liquid template. 2. Use `aliases` to extract variables from the tool's response body if the response is an array. ```json { "aliases": [ { "key": "customerName", "value": "{{$[0].name}}" }, { "key": "customerAge", "value": "{{$[0].age}}" } ] } ``` $ is a shorthand for the tool's response body. `$[0]` is the first item in the array. `$[n]` is the nth item in the array. Note, $ is available regardless of the response body type (both object and array). 3. Use `aliases` to extract variables from the tool's response headers. ```json { "aliases": [ { "key": "customerName", "value": "{{tool.response.headers.customer-name}}" }, { "key": "customerAge", "value": "{{tool.response.headers.customer-age}}" } ] } ``` `tool.response` is made available to the liquid template. Particularly, both `tool.response.headers` and `tool.response.body` are available. Note, `tool.response` is available regardless of the response body type (both object and array). 4. Use `schema` to extract a large portion of the tool's response body. 4.1. If you hit example.com and it returns `{"name": "John", "age": 30}`, then you can specify the schema as: ```json { "schema": { "type": "object", "properties": { "name": { "type": "string" }, "age": { "type": "number" } } } } ``` 4.2. If you hit example.com and it returns `{"name": {"first": "John", "last": "Doe"}}`, then you can specify the schema as: ```json { "schema": { "type": "object", "properties": { "name": { "type": "object", "properties": { "first": { "type": "string" }, "last": { "type": "string" } } } } } } ``` These will be extracted as `{{ name }}` and `{{ age }}` respectively. To emphasize, object properties are extracted as direct global variables. 4.3. If you hit example.com and it returns `{"name": {"first": "John", "last": "Doe"}}`, then you can specify the schema as: ```json { "schema": { "type": "object", "properties": { "name": { "type": "object", "properties": { "first": { "type": "string" }, "last": { "type": "string" } } } } } } ``` These will be extracted as `{{ name }}`. And, `{{ name.first }}` and `{{ name.last }}` will be accessible. 4.4. If you hit example.com and it returns `["94123", "94124"]`, then you can specify the schema as: ```json { "schema": { "type": "array", "title": "zipCodes", "items": { "type": "string" } } } ``` This will be extracted as `{{ zipCodes }}`. To access the array items, you can use `{{ zipCodes[0] }}` and `{{ zipCodes[1] }}`. 4.5. If you hit example.com and it returns `[{"name": "John", "age": 30, "zipCodes": ["94123", "94124"]}, {"name": "Jane", "age": 25, "zipCodes": ["94125", "94126"]}]`, then you can specify the schema as: ```json { "schema": { "type": "array", "title": "people", "items": { "type": "object", "properties": { "name": { "type": "string" }, "age": { "type": "number" }, "zipCodes": { "type": "array", "items": { "type": "string" } } } } } } ``` This will be extracted as `{{ people }}`. To access the array items, you can use `{{ people[n].name }}`, `{{ people[n].age }}`, `{{ people[n].zipCodes }}`, `{{ people[n].zipCodes[0] }}` and `{{ people[n].zipCodes[1] }}`. Note: Both `aliases` and `schema` can be used together. allOf: - $ref: '#/components/schemas/VariableExtractionPlan' function: description: >- This is the function definition of the tool. For `endCall`, `transferCall`, and `dtmf` tools, this is auto-filled based on tool-specific fields like `tool.destinations`. But, even in those cases, you can provide a custom function definition for advanced use cases. An example of an advanced use case is if you want to customize the message that's spoken for `endCall` tool. You can specify a function where it returns an argument "reason". Then, in `messages` array, you can have many "request-complete" messages. One of these messages will be triggered if the `messages[].conditions` matches the "reason" argument. allOf: - $ref: '#/components/schemas/OpenAIFunction' required: - type - method - url CreateBashToolDTO: type: object properties: messages: type: array description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. items: oneOf: - $ref: '#/components/schemas/ToolMessageStart' title: ToolMessageStart - $ref: '#/components/schemas/ToolMessageComplete' title: ToolMessageComplete - $ref: '#/components/schemas/ToolMessageFailed' title: ToolMessageFailed - $ref: '#/components/schemas/ToolMessageDelayed' title: ToolMessageDelayed type: type: string enum: - bash description: The type of tool. "bash" for Bash tool. subType: type: string enum: - bash_20241022 description: The sub type of tool. server: description: |2- This is the server where a `tool-calls` webhook will be sent. Notes: - Webhook is sent to this server when a tool call is made. - Webhook contains the call, assistant, and phone number objects. - Webhook contains the variables set on the assistant. - Webhook is sent to the first available URL in this order: {{tool.server.url}}, {{assistant.server.url}}, {{phoneNumber.server.url}}, {{org.server.url}}. - Webhook expects a response with tool call result. allOf: - $ref: '#/components/schemas/Server' name: type: string description: The name of the tool, fixed to 'bash' default: bash enum: - bash function: description: >- This is the function definition of the tool. For `endCall`, `transferCall`, and `dtmf` tools, this is auto-filled based on tool-specific fields like `tool.destinations`. But, even in those cases, you can provide a custom function definition for advanced use cases. An example of an advanced use case is if you want to customize the message that's spoken for `endCall` tool. You can specify a function where it returns an argument "reason". Then, in `messages` array, you can have many "request-complete" messages. One of these messages will be triggered if the `messages[].conditions` matches the "reason" argument. allOf: - $ref: '#/components/schemas/OpenAIFunction' required: - type - subType - name CreateComputerToolDTO: type: object properties: messages: type: array description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. items: oneOf: - $ref: '#/components/schemas/ToolMessageStart' title: ToolMessageStart - $ref: '#/components/schemas/ToolMessageComplete' title: ToolMessageComplete - $ref: '#/components/schemas/ToolMessageFailed' title: ToolMessageFailed - $ref: '#/components/schemas/ToolMessageDelayed' title: ToolMessageDelayed type: type: string enum: - computer description: The type of tool. "computer" for Computer tool. subType: type: string enum: - computer_20241022 description: The sub type of tool. server: description: |2- This is the server where a `tool-calls` webhook will be sent. Notes: - Webhook is sent to this server when a tool call is made. - Webhook contains the call, assistant, and phone number objects. - Webhook contains the variables set on the assistant. - Webhook is sent to the first available URL in this order: {{tool.server.url}}, {{assistant.server.url}}, {{phoneNumber.server.url}}, {{org.server.url}}. - Webhook expects a response with tool call result. allOf: - $ref: '#/components/schemas/Server' name: type: string description: The name of the tool, fixed to 'computer' default: computer enum: - computer displayWidthPx: type: number description: The display width in pixels displayHeightPx: type: number description: The display height in pixels displayNumber: type: number description: Optional display number function: description: >- This is the function definition of the tool. For `endCall`, `transferCall`, and `dtmf` tools, this is auto-filled based on tool-specific fields like `tool.destinations`. But, even in those cases, you can provide a custom function definition for advanced use cases. An example of an advanced use case is if you want to customize the message that's spoken for `endCall` tool. You can specify a function where it returns an argument "reason". Then, in `messages` array, you can have many "request-complete" messages. One of these messages will be triggered if the `messages[].conditions` matches the "reason" argument. allOf: - $ref: '#/components/schemas/OpenAIFunction' required: - type - subType - name - displayWidthPx - displayHeightPx CreateDtmfToolDTO: type: object properties: messages: type: array description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. items: oneOf: - $ref: '#/components/schemas/ToolMessageStart' title: ToolMessageStart - $ref: '#/components/schemas/ToolMessageComplete' title: ToolMessageComplete - $ref: '#/components/schemas/ToolMessageFailed' title: ToolMessageFailed - $ref: '#/components/schemas/ToolMessageDelayed' title: ToolMessageDelayed type: type: string enum: - dtmf description: The type of tool. "dtmf" for DTMF tool. function: description: >- This is the function definition of the tool. For `endCall`, `transferCall`, and `dtmf` tools, this is auto-filled based on tool-specific fields like `tool.destinations`. But, even in those cases, you can provide a custom function definition for advanced use cases. An example of an advanced use case is if you want to customize the message that's spoken for `endCall` tool. You can specify a function where it returns an argument "reason". Then, in `messages` array, you can have many "request-complete" messages. One of these messages will be triggered if the `messages[].conditions` matches the "reason" argument. allOf: - $ref: '#/components/schemas/OpenAIFunction' required: - type CreateEndCallToolDTO: type: object properties: messages: type: array description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. items: oneOf: - $ref: '#/components/schemas/ToolMessageStart' title: ToolMessageStart - $ref: '#/components/schemas/ToolMessageComplete' title: ToolMessageComplete - $ref: '#/components/schemas/ToolMessageFailed' title: ToolMessageFailed - $ref: '#/components/schemas/ToolMessageDelayed' title: ToolMessageDelayed type: type: string enum: - endCall description: The type of tool. "endCall" for End Call tool. function: description: >- This is the function definition of the tool. For `endCall`, `transferCall`, and `dtmf` tools, this is auto-filled based on tool-specific fields like `tool.destinations`. But, even in those cases, you can provide a custom function definition for advanced use cases. An example of an advanced use case is if you want to customize the message that's spoken for `endCall` tool. You can specify a function where it returns an argument "reason". Then, in `messages` array, you can have many "request-complete" messages. One of these messages will be triggered if the `messages[].conditions` matches the "reason" argument. allOf: - $ref: '#/components/schemas/OpenAIFunction' required: - type CreateFunctionToolDTO: type: object properties: messages: type: array description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. items: oneOf: - $ref: '#/components/schemas/ToolMessageStart' title: ToolMessageStart - $ref: '#/components/schemas/ToolMessageComplete' title: ToolMessageComplete - $ref: '#/components/schemas/ToolMessageFailed' title: ToolMessageFailed - $ref: '#/components/schemas/ToolMessageDelayed' title: ToolMessageDelayed type: type: string enum: - function description: The type of tool. "function" for Function tool. async: type: boolean example: false description: |- This determines if the tool is async. If async, the assistant will move forward without waiting for your server to respond. This is useful if you just want to trigger something on your server. If sync, the assistant will wait for your server to respond. This is useful if want assistant to respond with the result from your server. Defaults to synchronous (`false`). server: description: |2- This is the server where a `tool-calls` webhook will be sent. Notes: - Webhook is sent to this server when a tool call is made. - Webhook contains the call, assistant, and phone number objects. - Webhook contains the variables set on the assistant. - Webhook is sent to the first available URL in this order: {{tool.server.url}}, {{assistant.server.url}}, {{phoneNumber.server.url}}, {{org.server.url}}. - Webhook expects a response with tool call result. allOf: - $ref: '#/components/schemas/Server' function: description: >- This is the function definition of the tool. For `endCall`, `transferCall`, and `dtmf` tools, this is auto-filled based on tool-specific fields like `tool.destinations`. But, even in those cases, you can provide a custom function definition for advanced use cases. An example of an advanced use case is if you want to customize the message that's spoken for `endCall` tool. You can specify a function where it returns an argument "reason". Then, in `messages` array, you can have many "request-complete" messages. One of these messages will be triggered if the `messages[].conditions` matches the "reason" argument. allOf: - $ref: '#/components/schemas/OpenAIFunction' required: - type CreateGoHighLevelCalendarAvailabilityToolDTO: type: object properties: messages: type: array description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. items: oneOf: - $ref: '#/components/schemas/ToolMessageStart' title: ToolMessageStart - $ref: '#/components/schemas/ToolMessageComplete' title: ToolMessageComplete - $ref: '#/components/schemas/ToolMessageFailed' title: ToolMessageFailed - $ref: '#/components/schemas/ToolMessageDelayed' title: ToolMessageDelayed type: type: string enum: - gohighlevel.calendar.availability.check description: >- The type of tool. "gohighlevel.calendar.availability.check" for GoHighLevel Calendar availability check tool. function: description: >- This is the function definition of the tool. For `endCall`, `transferCall`, and `dtmf` tools, this is auto-filled based on tool-specific fields like `tool.destinations`. But, even in those cases, you can provide a custom function definition for advanced use cases. An example of an advanced use case is if you want to customize the message that's spoken for `endCall` tool. You can specify a function where it returns an argument "reason". Then, in `messages` array, you can have many "request-complete" messages. One of these messages will be triggered if the `messages[].conditions` matches the "reason" argument. allOf: - $ref: '#/components/schemas/OpenAIFunction' required: - type CreateGoHighLevelCalendarEventCreateToolDTO: type: object properties: messages: type: array description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. items: oneOf: - $ref: '#/components/schemas/ToolMessageStart' title: ToolMessageStart - $ref: '#/components/schemas/ToolMessageComplete' title: ToolMessageComplete - $ref: '#/components/schemas/ToolMessageFailed' title: ToolMessageFailed - $ref: '#/components/schemas/ToolMessageDelayed' title: ToolMessageDelayed type: type: string enum: - gohighlevel.calendar.event.create description: >- The type of tool. "gohighlevel.calendar.event.create" for GoHighLevel Calendar event create tool. function: description: >- This is the function definition of the tool. For `endCall`, `transferCall`, and `dtmf` tools, this is auto-filled based on tool-specific fields like `tool.destinations`. But, even in those cases, you can provide a custom function definition for advanced use cases. An example of an advanced use case is if you want to customize the message that's spoken for `endCall` tool. You can specify a function where it returns an argument "reason". Then, in `messages` array, you can have many "request-complete" messages. One of these messages will be triggered if the `messages[].conditions` matches the "reason" argument. allOf: - $ref: '#/components/schemas/OpenAIFunction' required: - type CreateGoHighLevelContactCreateToolDTO: type: object properties: messages: type: array description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. items: oneOf: - $ref: '#/components/schemas/ToolMessageStart' title: ToolMessageStart - $ref: '#/components/schemas/ToolMessageComplete' title: ToolMessageComplete - $ref: '#/components/schemas/ToolMessageFailed' title: ToolMessageFailed - $ref: '#/components/schemas/ToolMessageDelayed' title: ToolMessageDelayed type: type: string enum: - gohighlevel.contact.create description: >- The type of tool. "gohighlevel.contact.create" for GoHighLevel contact create tool. function: description: >- This is the function definition of the tool. For `endCall`, `transferCall`, and `dtmf` tools, this is auto-filled based on tool-specific fields like `tool.destinations`. But, even in those cases, you can provide a custom function definition for advanced use cases. An example of an advanced use case is if you want to customize the message that's spoken for `endCall` tool. You can specify a function where it returns an argument "reason". Then, in `messages` array, you can have many "request-complete" messages. One of these messages will be triggered if the `messages[].conditions` matches the "reason" argument. allOf: - $ref: '#/components/schemas/OpenAIFunction' required: - type CreateGoHighLevelContactGetToolDTO: type: object properties: messages: type: array description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. items: oneOf: - $ref: '#/components/schemas/ToolMessageStart' title: ToolMessageStart - $ref: '#/components/schemas/ToolMessageComplete' title: ToolMessageComplete - $ref: '#/components/schemas/ToolMessageFailed' title: ToolMessageFailed - $ref: '#/components/schemas/ToolMessageDelayed' title: ToolMessageDelayed type: type: string enum: - gohighlevel.contact.get description: >- The type of tool. "gohighlevel.contact.get" for GoHighLevel contact get tool. function: description: >- This is the function definition of the tool. For `endCall`, `transferCall`, and `dtmf` tools, this is auto-filled based on tool-specific fields like `tool.destinations`. But, even in those cases, you can provide a custom function definition for advanced use cases. An example of an advanced use case is if you want to customize the message that's spoken for `endCall` tool. You can specify a function where it returns an argument "reason". Then, in `messages` array, you can have many "request-complete" messages. One of these messages will be triggered if the `messages[].conditions` matches the "reason" argument. allOf: - $ref: '#/components/schemas/OpenAIFunction' required: - type CreateGoogleCalendarCheckAvailabilityToolDTO: type: object properties: messages: type: array description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. items: oneOf: - $ref: '#/components/schemas/ToolMessageStart' title: ToolMessageStart - $ref: '#/components/schemas/ToolMessageComplete' title: ToolMessageComplete - $ref: '#/components/schemas/ToolMessageFailed' title: ToolMessageFailed - $ref: '#/components/schemas/ToolMessageDelayed' title: ToolMessageDelayed type: type: string enum: - google.calendar.availability.check description: >- The type of tool. "google.calendar.availability.check" for Google Calendar availability check tool. function: description: >- This is the function definition of the tool. For `endCall`, `transferCall`, and `dtmf` tools, this is auto-filled based on tool-specific fields like `tool.destinations`. But, even in those cases, you can provide a custom function definition for advanced use cases. An example of an advanced use case is if you want to customize the message that's spoken for `endCall` tool. You can specify a function where it returns an argument "reason". Then, in `messages` array, you can have many "request-complete" messages. One of these messages will be triggered if the `messages[].conditions` matches the "reason" argument. allOf: - $ref: '#/components/schemas/OpenAIFunction' required: - type CreateGoogleCalendarCreateEventToolDTO: type: object properties: messages: type: array description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. items: oneOf: - $ref: '#/components/schemas/ToolMessageStart' title: ToolMessageStart - $ref: '#/components/schemas/ToolMessageComplete' title: ToolMessageComplete - $ref: '#/components/schemas/ToolMessageFailed' title: ToolMessageFailed - $ref: '#/components/schemas/ToolMessageDelayed' title: ToolMessageDelayed type: type: string enum: - google.calendar.event.create description: >- The type of tool. "google.calendar.event.create" for Google Calendar tool. function: description: >- This is the function definition of the tool. For `endCall`, `transferCall`, and `dtmf` tools, this is auto-filled based on tool-specific fields like `tool.destinations`. But, even in those cases, you can provide a custom function definition for advanced use cases. An example of an advanced use case is if you want to customize the message that's spoken for `endCall` tool. You can specify a function where it returns an argument "reason". Then, in `messages` array, you can have many "request-complete" messages. One of these messages will be triggered if the `messages[].conditions` matches the "reason" argument. allOf: - $ref: '#/components/schemas/OpenAIFunction' required: - type CreateGoogleSheetsRowAppendToolDTO: type: object properties: messages: type: array description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. items: oneOf: - $ref: '#/components/schemas/ToolMessageStart' title: ToolMessageStart - $ref: '#/components/schemas/ToolMessageComplete' title: ToolMessageComplete - $ref: '#/components/schemas/ToolMessageFailed' title: ToolMessageFailed - $ref: '#/components/schemas/ToolMessageDelayed' title: ToolMessageDelayed type: type: string enum: - google.sheets.row.append description: The type of tool. "google.sheets.row.append" for Google Sheets tool. function: description: >- This is the function definition of the tool. For `endCall`, `transferCall`, and `dtmf` tools, this is auto-filled based on tool-specific fields like `tool.destinations`. But, even in those cases, you can provide a custom function definition for advanced use cases. An example of an advanced use case is if you want to customize the message that's spoken for `endCall` tool. You can specify a function where it returns an argument "reason". Then, in `messages` array, you can have many "request-complete" messages. One of these messages will be triggered if the `messages[].conditions` matches the "reason" argument. allOf: - $ref: '#/components/schemas/OpenAIFunction' required: - type CreateMcpToolDTO: type: object properties: messages: type: array description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. items: oneOf: - $ref: '#/components/schemas/ToolMessageStart' title: ToolMessageStart - $ref: '#/components/schemas/ToolMessageComplete' title: ToolMessageComplete - $ref: '#/components/schemas/ToolMessageFailed' title: ToolMessageFailed - $ref: '#/components/schemas/ToolMessageDelayed' title: ToolMessageDelayed type: type: string enum: - mcp description: The type of tool. "mcp" for MCP tool. server: description: |2- This is the server where a `tool-calls` webhook will be sent. Notes: - Webhook is sent to this server when a tool call is made. - Webhook contains the call, assistant, and phone number objects. - Webhook contains the variables set on the assistant. - Webhook is sent to the first available URL in this order: {{tool.server.url}}, {{assistant.server.url}}, {{phoneNumber.server.url}}, {{org.server.url}}. - Webhook expects a response with tool call result. allOf: - $ref: '#/components/schemas/Server' metadata: $ref: '#/components/schemas/McpToolMetadata' function: description: >- This is the function definition of the tool. For `endCall`, `transferCall`, and `dtmf` tools, this is auto-filled based on tool-specific fields like `tool.destinations`. But, even in those cases, you can provide a custom function definition for advanced use cases. An example of an advanced use case is if you want to customize the message that's spoken for `endCall` tool. You can specify a function where it returns an argument "reason". Then, in `messages` array, you can have many "request-complete" messages. One of these messages will be triggered if the `messages[].conditions` matches the "reason" argument. allOf: - $ref: '#/components/schemas/OpenAIFunction' required: - type CreateQueryToolDTO: type: object properties: messages: type: array description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. items: oneOf: - $ref: '#/components/schemas/ToolMessageStart' title: ToolMessageStart - $ref: '#/components/schemas/ToolMessageComplete' title: ToolMessageComplete - $ref: '#/components/schemas/ToolMessageFailed' title: ToolMessageFailed - $ref: '#/components/schemas/ToolMessageDelayed' title: ToolMessageDelayed type: type: string enum: - query description: The type of tool. "query" for Query tool. knowledgeBases: description: The knowledge bases to query type: array items: $ref: '#/components/schemas/KnowledgeBase' function: description: >- This is the function definition of the tool. For `endCall`, `transferCall`, and `dtmf` tools, this is auto-filled based on tool-specific fields like `tool.destinations`. But, even in those cases, you can provide a custom function definition for advanced use cases. An example of an advanced use case is if you want to customize the message that's spoken for `endCall` tool. You can specify a function where it returns an argument "reason". Then, in `messages` array, you can have many "request-complete" messages. One of these messages will be triggered if the `messages[].conditions` matches the "reason" argument. allOf: - $ref: '#/components/schemas/OpenAIFunction' required: - type CreateSlackSendMessageToolDTO: type: object properties: messages: type: array description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. items: oneOf: - $ref: '#/components/schemas/ToolMessageStart' title: ToolMessageStart - $ref: '#/components/schemas/ToolMessageComplete' title: ToolMessageComplete - $ref: '#/components/schemas/ToolMessageFailed' title: ToolMessageFailed - $ref: '#/components/schemas/ToolMessageDelayed' title: ToolMessageDelayed type: type: string enum: - slack.message.send description: The type of tool. "slack.message.send" for Slack send message tool. function: description: >- This is the function definition of the tool. For `endCall`, `transferCall`, and `dtmf` tools, this is auto-filled based on tool-specific fields like `tool.destinations`. But, even in those cases, you can provide a custom function definition for advanced use cases. An example of an advanced use case is if you want to customize the message that's spoken for `endCall` tool. You can specify a function where it returns an argument "reason". Then, in `messages` array, you can have many "request-complete" messages. One of these messages will be triggered if the `messages[].conditions` matches the "reason" argument. allOf: - $ref: '#/components/schemas/OpenAIFunction' required: - type CreateSmsToolDTO: type: object properties: messages: type: array description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. items: oneOf: - $ref: '#/components/schemas/ToolMessageStart' title: ToolMessageStart - $ref: '#/components/schemas/ToolMessageComplete' title: ToolMessageComplete - $ref: '#/components/schemas/ToolMessageFailed' title: ToolMessageFailed - $ref: '#/components/schemas/ToolMessageDelayed' title: ToolMessageDelayed type: type: string enum: - sms description: The type of tool. "sms" for Twilio SMS sending tool. function: description: >- This is the function definition of the tool. For `endCall`, `transferCall`, and `dtmf` tools, this is auto-filled based on tool-specific fields like `tool.destinations`. But, even in those cases, you can provide a custom function definition for advanced use cases. An example of an advanced use case is if you want to customize the message that's spoken for `endCall` tool. You can specify a function where it returns an argument "reason". Then, in `messages` array, you can have many "request-complete" messages. One of these messages will be triggered if the `messages[].conditions` matches the "reason" argument. allOf: - $ref: '#/components/schemas/OpenAIFunction' required: - type CreateTextEditorToolDTO: type: object properties: messages: type: array description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. items: oneOf: - $ref: '#/components/schemas/ToolMessageStart' title: ToolMessageStart - $ref: '#/components/schemas/ToolMessageComplete' title: ToolMessageComplete - $ref: '#/components/schemas/ToolMessageFailed' title: ToolMessageFailed - $ref: '#/components/schemas/ToolMessageDelayed' title: ToolMessageDelayed type: type: string enum: - textEditor description: The type of tool. "textEditor" for Text Editor tool. subType: type: string enum: - text_editor_20241022 description: The sub type of tool. server: description: |2- This is the server where a `tool-calls` webhook will be sent. Notes: - Webhook is sent to this server when a tool call is made. - Webhook contains the call, assistant, and phone number objects. - Webhook contains the variables set on the assistant. - Webhook is sent to the first available URL in this order: {{tool.server.url}}, {{assistant.server.url}}, {{phoneNumber.server.url}}, {{org.server.url}}. - Webhook expects a response with tool call result. allOf: - $ref: '#/components/schemas/Server' name: type: string description: The name of the tool, fixed to 'str_replace_editor' default: str_replace_editor enum: - str_replace_editor function: description: >- This is the function definition of the tool. For `endCall`, `transferCall`, and `dtmf` tools, this is auto-filled based on tool-specific fields like `tool.destinations`. But, even in those cases, you can provide a custom function definition for advanced use cases. An example of an advanced use case is if you want to customize the message that's spoken for `endCall` tool. You can specify a function where it returns an argument "reason". Then, in `messages` array, you can have many "request-complete" messages. One of these messages will be triggered if the `messages[].conditions` matches the "reason" argument. allOf: - $ref: '#/components/schemas/OpenAIFunction' required: - type - subType - name CreateTransferCallToolDTO: type: object properties: messages: type: array description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. items: oneOf: - $ref: '#/components/schemas/ToolMessageStart' title: ToolMessageStart - $ref: '#/components/schemas/ToolMessageComplete' title: ToolMessageComplete - $ref: '#/components/schemas/ToolMessageFailed' title: ToolMessageFailed - $ref: '#/components/schemas/ToolMessageDelayed' title: ToolMessageDelayed type: type: string enum: - transferCall destinations: type: array description: >- These are the destinations that the call can be transferred to. If no destinations are provided, server.url will be used to get the transfer destination once the tool is called. items: oneOf: - $ref: '#/components/schemas/TransferDestinationAssistant' title: Assistant - $ref: '#/components/schemas/TransferDestinationNumber' title: Number - $ref: '#/components/schemas/TransferDestinationSip' title: Sip function: description: >- This is the function definition of the tool. For `endCall`, `transferCall`, and `dtmf` tools, this is auto-filled based on tool-specific fields like `tool.destinations`. But, even in those cases, you can provide a custom function definition for advanced use cases. An example of an advanced use case is if you want to customize the message that's spoken for `endCall` tool. You can specify a function where it returns an argument "reason". Then, in `messages` array, you can have many "request-complete" messages. One of these messages will be triggered if the `messages[].conditions` matches the "reason" argument. allOf: - $ref: '#/components/schemas/OpenAIFunction' required: - type CreateCustomKnowledgeBaseDTO: type: object properties: provider: type: string description: This knowledge base is bring your own knowledge base implementation. enum: - custom-knowledge-base server: description: |- This is where the knowledge base request will be sent. Request Example: POST https://{server.url} Content-Type: application/json { "messsage": { "type": "knowledge-base-request", "messages": [ { "role": "user", "content": "Why is ocean blue?" } ], ...other metadata about the call... } } Response Expected: ``` { "message": { "role": "assistant", "content": "The ocean is blue because water absorbs everything but blue.", }, // YOU CAN RETURN THE EXACT RESPONSE TO SPEAK "documents": [ { "content": "The ocean is blue primarily because water absorbs colors in the red part of the light spectrum and scatters the blue light, making it more visible to our eyes.", "similarity": 1 }, { "content": "Blue light is scattered more by the water molecules than other colors, enhancing the blue appearance of the ocean.", "similarity": .5 } ] // OR, YOU CAN RETURN AN ARRAY OF DOCUMENTS THAT WILL BE SENT TO THE MODEL } ``` allOf: - $ref: '#/components/schemas/Server' required: - provider - server AnthropicThinkingConfig: type: object properties: type: type: string enum: - enabled budgetTokens: type: number description: |- The maximum number of tokens to allocate for thinking. Must be between 1024 and 100000 tokens. minimum: 1024 maximum: 100000 required: - type - budgetTokens GoogleRealtimeConfig: type: object properties: topP: type: number description: >- This is the nucleus sampling parameter that controls the cumulative probability of tokens considered during text generation. Only applicable with the Gemini Flash 2.0 Multimodal Live API. topK: type: number description: >- This is the top-k sampling parameter that limits the number of highest probability tokens considered during text generation. Only applicable with the Gemini Flash 2.0 Multimodal Live API. presencePenalty: type: number description: >- This is the presence penalty parameter that influences the model's likelihood to repeat information by penalizing tokens based on their presence in the text. Only applicable with the Gemini Flash 2.0 Multimodal Live API. frequencyPenalty: type: number description: >- This is the frequency penalty parameter that influences the model's likelihood to repeat tokens by penalizing them based on their frequency in the text. Only applicable with the Gemini Flash 2.0 Multimodal Live API. speechConfig: description: >- This is the speech configuration object that defines the voice settings to be used for the model's speech output. Only applicable with the Gemini Flash 2.0 Multimodal Live API. allOf: - $ref: '#/components/schemas/GeminiMultimodalLiveSpeechConfig' ChunkPlan: type: object properties: enabled: type: boolean description: >- This determines whether the model output is chunked before being sent to the voice provider. Default `true`. Usage: - To rely on the voice provider's audio generation logic, set this to `false`. - If seeing issues with quality, set this to `true`. If disabled, cozmox-provided audio control tokens like will not work. @default true example: true minCharacters: type: number description: |- This is the minimum number of characters in a chunk. Usage: - To increase quality, set this to a higher value. - To decrease latency, set this to a lower value. @default 30 minimum: 1 maximum: 80 example: 30 punctuationBoundaries: type: array description: >- These are the punctuations that are considered valid boundaries for a chunk to be created. Usage: - To increase quality, constrain to fewer boundaries. - To decrease latency, enable all. Default is automatically set to balance the trade-off between quality and latency based on the provider. enum: - 。 - ， - . - '!' - '?' - ; - ) - ، - ۔ - । - ॥ - '|' - '||' - ',' - ':' example: - 。 - ， - . - '!' - '?' - ; - ، - ۔ - । - ॥ - '|' - '||' - ',' - ':' items: type: string enum: - 。 - ， - . - '!' - '?' - ; - ) - ، - ۔ - । - ॥ - '|' - '||' - ',' - ':' formatPlan: description: >- This is the plan for formatting the chunk before it is sent to the voice provider. allOf: - $ref: '#/components/schemas/FormatPlan' FallbackPlan: type: object properties: voices: type: array description: >- This is the list of voices to fallback to in the event that the primary voice provider fails. items: oneOf: - $ref: '#/components/schemas/FallbackAzureVoice' title: Azure - $ref: '#/components/schemas/FallbackCartesiaVoice' title: Cartesia - $ref: '#/components/schemas/FallbackHumeVoice' title: Hume - $ref: '#/components/schemas/FallbackCustomVoice' title: CustomVoice - $ref: '#/components/schemas/FallbackDeepgramVoice' title: Deepgram - $ref: '#/components/schemas/FallbackElevenLabsVoice' title: ElevenLabs - $ref: '#/components/schemas/FallbackcozmoxVoice' title: cozmox - $ref: '#/components/schemas/FallbackLMNTVoice' title: LMNT - $ref: '#/components/schemas/FallbackOpenAIVoice' title: OpenAI - $ref: '#/components/schemas/FallbackPlayHTVoice' title: PlayHT - $ref: '#/components/schemas/FallbackRimeAIVoice' title: RimeAI - $ref: '#/components/schemas/FallbackSmallestAIVoice' title: Smallest AI - $ref: '#/components/schemas/FallbackTavusVoice' title: TavusVoice - $ref: '#/components/schemas/FallbackNeuphonicVoice' title: Neuphonic - $ref: '#/components/schemas/FallbackSesameVoice' title: Sesame - $ref: '#/components/schemas/FallbackInworldVoice' title: Inworld required: - voices CartesiaExperimentalControls: type: object properties: speed: oneOf: - type: string enum: - slowest - slow - normal - fast - fastest example: normal - type: number minimum: -1 maximum: 1 example: 0.5 emotion: type: string enum: - anger:lowest - anger:low - anger:high - anger:highest - positivity:lowest - positivity:low - positivity:high - positivity:highest - surprise:lowest - surprise:low - surprise:high - surprise:highest - sadness:lowest - sadness:low - sadness:high - sadness:highest - curiosity:lowest - curiosity:low - curiosity:high - curiosity:highest example: - happiness:high TavusConversationProperties: type: object properties: maxCallDuration: type: number description: >- The maximum duration of the call in seconds. The default `maxCallDuration` is 3600 seconds (1 hour). Once the time limit specified by this parameter has been reached, the conversation will automatically shut down. participantLeftTimeout: type: number description: >- The duration in seconds after which the call will be automatically shut down once the last participant leaves. participantAbsentTimeout: type: number description: >- Starting from conversation creation, the duration in seconds after which the call will be automatically shut down if no participant joins the call. Default is 300 seconds (5 minutes). enableRecording: type: boolean description: If true, the user will be able to record the conversation. enableTranscription: type: boolean description: >- If true, the user will be able to transcribe the conversation. You can find more instructions on displaying transcriptions if you are using your custom DailyJS components here. You need to have an event listener on Daily that listens for `app-messages`. applyGreenscreen: type: boolean description: >- If true, the background will be replaced with a greenscreen (RGB values: `[0, 255, 155]`). You can use WebGL on the frontend to make the greenscreen transparent or change its color. language: type: string description: >- The language of the conversation. Please provide the **full language name**, not the two-letter code. If you are using your own TTS voice, please ensure it supports the language you provide. If you are using a stock replica or default persona, please note that only ElevenLabs and Cartesia supported languages are available. You can find a full list of supported languages for Cartesia here, for ElevenLabs here, and for PlayHT here. recordingS3BucketName: type: string description: The name of the S3 bucket where the recording will be stored. recordingS3BucketRegion: type: string description: The region of the S3 bucket where the recording will be stored. awsAssumeRoleArn: type: string description: The ARN of the role that will be assumed to access the S3 bucket. VoicemailDetectionBackoffPlan: type: object properties: startAtSeconds: type: number description: >- This is the number of seconds to wait before starting the first retry attempt. minimum: 0 default: 5 frequencySeconds: type: number description: This is the interval in seconds between retry attempts. minimum: 2.5 default: 5 maxRetries: type: number description: This is the maximum number of retry attempts before giving up. minimum: 1 maximum: 10 default: 6 AzureBlobStorageBucketPlan: type: object properties: connectionString: type: string description: This is the blob storage connection string for the Azure resource. containerName: type: string description: This is the container name for the Azure blob storage. path: type: string description: >- This is the path where call artifacts will be stored. Usage: - To store call artifacts in a specific folder, set this to the full path. Eg. "/folder-name1/folder-name2". - To store call artifacts in the root of the bucket, leave this blank. @default "/" required: - connectionString - containerName SipTrunkGateway: type: object properties: ip: type: string description: >- This is the address of the gateway. It can be an IPv4 address like 1.1.1.1 or a fully qualified domain name like my-sip-trunk.pstn.twilio.com. port: type: number description: |- This is the port number of the gateway. Default is 5060. @default 5060 minimum: 1 maximum: 65535 netmask: type: number description: |- This is the netmask of the gateway. Defaults to 32. @default 32 minimum: 24 maximum: 32 inboundEnabled: type: boolean description: >- This is whether inbound calls are allowed from this gateway. Default is true. @default true outboundEnabled: type: boolean description: >- This is whether outbound calls should be sent to this gateway. Default is true. Note, if netmask is less than 32, it doesn't affect the outbound IPs that are tried. 1 attempt is made to `ip:port`. @default true outboundProtocol: type: string description: >- This is the protocol to use for SIP signaling outbound calls. Default is udp. @default udp enum: - tls/srtp - tcp - tls - udp optionsPingEnabled: type: boolean description: >- This is whether to send options ping to the gateway. This can be used to check if the gateway is reachable. Default is false. This is useful for high availability setups where you want to check if the gateway is reachable before routing calls to it. Note, if no gateway for a trunk is reachable, outbound calls will be rejected. @default false required: - ip SipTrunkOutboundAuthenticationPlan: type: object properties: authPassword: type: string description: This is not returned in the API. authUsername: type: string sipRegisterPlan: description: >- This can be used to configure if SIP register is required by the SIP trunk. If not provided, no SIP registration will be attempted. allOf: - $ref: '#/components/schemas/SipTrunkOutboundSipRegisterPlan' SbcConfiguration: type: object properties: {} CloudflareR2BucketPlan: type: object properties: accessKeyId: type: string description: Cloudflare R2 Access key ID. secretAccessKey: type: string description: Cloudflare R2 access key secret. This is not returned in the API. url: type: string description: Cloudflare R2 base url. name: type: string description: This is the name of the bucket. path: type: string description: >- This is the path where call artifacts will be stored. Usage: - To store call artifacts in a specific folder, set this to the full path. Eg. "/folder-name1/folder-name2". - To store call artifacts in the root of the bucket, leave this blank. @default "/" required: - name OAuth2AuthenticationPlan: type: object properties: type: type: string enum: - oauth2 url: type: string description: This is the OAuth2 URL. clientId: type: string description: This is the OAuth2 client ID. clientSecret: type: string description: This is the OAuth2 client secret. scope: type: string description: This is the scope of the OAuth2 token. maxLength: 1000 required: - type - url - clientId - clientSecret GcpKey: type: object properties: type: type: string description: This is the type of the key. Most likely, this is "service_account". projectId: type: string description: This is the ID of the Google Cloud project associated with this key. privateKeyId: type: string description: This is the unique identifier for the private key. privateKey: type: string description: |- This is the private key in PEM format. Note: This is not returned in the API. clientEmail: type: string description: This is the email address associated with the service account. clientId: type: string description: This is the unique identifier for the client. authUri: type: string description: This is the URI for the auth provider's authorization endpoint. tokenUri: type: string description: This is the URI for the auth provider's token endpoint. authProviderX509CertUrl: type: string description: >- This is the URL of the public x509 certificate for the auth provider. clientX509CertUrl: type: string description: This is the URL of the public x509 certificate for the client. universeDomain: type: string description: >- This is the domain associated with the universe this service account belongs to. required: - type - projectId - privateKeyId - privateKey - clientEmail - clientId - authUri - tokenUri - authProviderX509CertUrl - clientX509CertUrl - universeDomain BucketPlan: type: object properties: name: type: string description: This is the name of the bucket. region: type: string description: >- This is the region of the bucket. Usage: - If `credential.type` is `aws`, then this is required. - If `credential.type` is `gcp`, then this is optional since GCP allows buckets to be accessed without a region but region is required for data residency requirements. Read here: https://cloud.google.com/storage/docs/request-endpoints This overrides the `credential.region` field if it is provided. path: type: string description: >- This is the path where call artifacts will be stored. Usage: - To store call artifacts in a specific folder, set this to the full path. Eg. "/folder-name1/folder-name2". - To store call artifacts in the root of the bucket, leave this blank. @default "/" hmacAccessKey: type: string description: >- This is the HMAC access key offered by GCP for interoperability with S3 clients. Here is the guide on how to create: https://cloud.google.com/storage/docs/authentication/managing-hmackeys#console Usage: - If `credential.type` is `gcp`, then this is required. - If `credential.type` is `aws`, then this is not required since credential.awsAccessKeyId is used instead. hmacSecret: type: string description: >- This is the secret for the HMAC access key. Here is the guide on how to create: https://cloud.google.com/storage/docs/authentication/managing-hmackeys#console Usage: - If `credential.type` is `gcp`, then this is required. - If `credential.type` is `aws`, then this is not required since credential.awsSecretAccessKey is used instead. Note: This is not returned in the API. required: - name SupabaseBucketPlan: type: object properties: region: type: string description: >- This is the S3 Region. It should look like us-east-1 It should be one of the supabase regions defined in the SUPABASE_REGION enum Check https://supabase.com/docs/guides/platform/regions for up to date regions enum: - us-west-1 - us-east-1 - us-east-2 - ca-central-1 - eu-west-1 - eu-west-2 - eu-west-3 - eu-central-1 - eu-central-2 - eu-north-1 - ap-south-1 - ap-southeast-1 - ap-northeast-1 - ap-northeast-2 - ap-southeast-2 - sa-east-1 url: type: string description: |- This is the S3 compatible URL for Supabase S3 This should look like https://.supabase.co/storage/v1/s3 accessKeyId: type: string description: |- This is the Supabase S3 Access Key ID. The user creates this in the Supabase project Storage settings secretAccessKey: type: string description: >- This is the Supabase S3 Secret Access Key. The user creates this in the Supabase project Storage settings along with the access key id name: type: string description: >- This is the Supabase S3 Bucket Name. The user must create this in Supabase under Storage > Buckets A bucket that does not exist will not be checked now, but file uploads will fail path: type: string description: >- This is the Supabase S3 Bucket Folder Path. The user can create this in Supabase under Storage > Buckets A path that does not exist will not be checked now, but file uploads will fail A Path is like a folder in the bucket Eg. If the bucket is called "my-bucket" and the path is "my-folder", the full path is "my-bucket/my-folder" required: - region - url - accessKeyId - secretAccessKey - name HMACAuthenticationPlan: type: object properties: type: type: string enum: - hmac secretKey: type: string description: This is the HMAC secret key used to sign requests. algorithm: type: string enum: - sha256 - sha512 - sha1 description: This is the HMAC algorithm to use for signing. signatureHeader: type: string description: >- This is the header name where the signature will be sent. Defaults to 'x-signature'. timestampHeader: type: string description: >- This is the header name where the timestamp will be sent. Defaults to 'x-timestamp'. signaturePrefix: type: string description: >- This is the prefix for the signature. For example, 'sha256=' for GitHub-style signatures. includeTimestamp: type: boolean description: >- Whether to include a timestamp in the signature payload. Defaults to true. payloadFormat: type: string description: >- Custom payload format. Use {body} for request body, {timestamp} for timestamp, {method} for HTTP method, {url} for URL, {svix-id} for unique message ID. Defaults to '{timestamp}.{body}'. messageIdHeader: type: string description: >- This is the header name where the unique message ID will be sent. Used for Svix-style webhooks. signatureEncoding: type: string enum: - hex - base64 description: The encoding format for the signature. Defaults to 'hex'. secretIsBase64: type: boolean description: >- Whether the secret key is base64-encoded and should be decoded before use. Defaults to false. required: - type - secretKey - algorithm Oauth2AuthenticationSession: type: object properties: accessToken: type: string description: This is the OAuth2 access token. expiresAt: format: date-time type: string description: This is the OAuth2 access token expiration. refreshToken: type: string description: This is the OAuth2 refresh token. TransferAssistantHookAction: type: object properties: type: type: string description: This is the type of action - must be "transfer" enum: - transfer destination: description: >- This is the destination details for the transfer - can be a phone number or SIP URI oneOf: - $ref: '#/components/schemas/TransferDestinationNumber' title: NumberTransferDestination - $ref: '#/components/schemas/TransferDestinationSip' title: SipTransferDestination required: - type FunctionCallAssistantHookAction: type: object properties: messages: type: array description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. items: oneOf: - $ref: '#/components/schemas/ToolMessageStart' title: ToolMessageStart - $ref: '#/components/schemas/ToolMessageComplete' title: ToolMessageComplete - $ref: '#/components/schemas/ToolMessageFailed' title: ToolMessageFailed - $ref: '#/components/schemas/ToolMessageDelayed' title: ToolMessageDelayed type: type: string enum: - function description: The type of tool. "function" for Function tool. async: type: boolean example: false description: |- This determines if the tool is async. If async, the assistant will move forward without waiting for your server to respond. This is useful if you just want to trigger something on your server. If sync, the assistant will wait for your server to respond. This is useful if want assistant to respond with the result from your server. Defaults to synchronous (`false`). server: description: |2- This is the server where a `tool-calls` webhook will be sent. Notes: - Webhook is sent to this server when a tool call is made. - Webhook contains the call, assistant, and phone number objects. - Webhook contains the variables set on the assistant. - Webhook is sent to the first available URL in this order: {{tool.server.url}}, {{assistant.server.url}}, {{phoneNumber.server.url}}, {{org.server.url}}. - Webhook expects a response with tool call result. allOf: - $ref: '#/components/schemas/Server' function: description: >- This is the function definition of the tool. For `endCall`, `transferCall`, and `dtmf` tools, this is auto-filled based on tool-specific fields like `tool.destinations`. But, even in those cases, you can provide a custom function definition for advanced use cases. An example of an advanced use case is if you want to customize the message that's spoken for `endCall` tool. You can specify a function where it returns an argument "reason". Then, in `messages` array, you can have many "request-complete" messages. One of these messages will be triggered if the `messages[].conditions` matches the "reason" argument. allOf: - $ref: '#/components/schemas/OpenAIFunction' required: - type AssistantHookFilter: type: object properties: type: type: string description: This is the type of filter - currently only "oneOf" is supported enum: - oneOf maxLength: 1000 key: type: string description: This is the key to filter on (e.g. "call.endedReason") maxLength: 1000 oneOf: description: This is the array of possible values to match against type: array items: type: string maxLength: 1000 required: - type - key - oneOf SayAssistantHookAction: type: object properties: type: type: string description: This is the type of action - must be "say" enum: - say exact: type: object description: This is the message to say required: - type - exact SmartDenoisingPlan: type: object properties: enabled: type: boolean description: Whether smart denoising using Krisp is enabled. default: false FourierDenoisingPlan: type: object properties: enabled: type: boolean description: >- Whether Fourier denoising is enabled. Note that this is experimental and may not work as expected. default: false mediaDetectionEnabled: type: boolean description: >- Whether automatic media detection is enabled. When enabled, the filter will automatically detect consistent background TV/music/radio and switch to more aggressive filtering settings. Only applies when enabled is true. example: true default: true staticThreshold: type: number description: >- Static threshold in dB used as fallback when no baseline is established. example: -35 minimum: -80 maximum: 0 default: -35 baselineOffsetDb: type: number description: >- How far below the rolling baseline to filter audio, in dB. Lower values (e.g., -10) are more aggressive, higher values (e.g., -20) are more conservative. example: -15 minimum: -30 maximum: -5 default: -15 windowSizeMs: type: number description: >- Rolling window size in milliseconds for calculating the audio baseline. Larger windows adapt more slowly but are more stable. example: 3000 minimum: 1000 maximum: 30000 default: 3000 baselinePercentile: type: number description: >- Percentile to use for baseline calculation (1-99). Higher percentiles (e.g., 85) focus on louder speech, lower percentiles (e.g., 50) include quieter speech. example: 85 minimum: 1 maximum: 99 default: 85 SummaryPlan: type: object properties: messages: description: >- These are the messages used to generate the summary. @default: ``` [ { "role": "system", "content": "You are an expert note-taker. You will be given a transcript of a call. Summarize the call in 2-3 sentences. DO NOT return anything except the summary." }, { "role": "user", "content": "Here is the transcript:\n\n{{transcript}}\n\n. Here is the ended reason of the call:\n\n{{endedReason}}\n\n" } ]``` You can customize by providing any messages you want. Here are the template variables available: - {{transcript}}: The transcript of the call from `call.artifact.transcript` - {{systemPrompt}}: The system prompt of the call from `assistant.model.messages[type=system].content` - {{endedReason}}: The ended reason of the call from `call.endedReason` type: array items: type: object enabled: type: boolean description: >- This determines whether a summary is generated and stored in `call.analysis.summary`. Defaults to true. Usage: - If you want to disable the summary, set this to false. @default true timeoutSeconds: type: number description: >- This is how long the request is tried before giving up. When request times out, `call.analysis.summary` will be empty. Usage: - To guarantee the summary is generated, set this value high. Note, this will delay the end of call report in cases where model is slow to respond. @default 5 seconds minimum: 1 maximum: 60 StructuredDataPlan: type: object properties: messages: description: >- These are the messages used to generate the structured data. @default: ``` [ { "role": "system", "content": "You are an expert data extractor. You will be given a transcript of a call. Extract structured data per the JSON Schema. DO NOT return anything except the structured data.\n\nJson Schema:\\n{{schema}}\n\nOnly respond with the JSON." }, { "role": "user", "content": "Here is the transcript:\n\n{{transcript}}\n\n. Here is the ended reason of the call:\n\n{{endedReason}}\n\n" } ]``` You can customize by providing any messages you want. Here are the template variables available: - {{transcript}}: the transcript of the call from `call.artifact.transcript`- {{systemPrompt}}: the system prompt of the call from `assistant.model.messages[type=system].content`- {{schema}}: the schema of the structured data from `structuredDataPlan.schema`- {{endedReason}}: the ended reason of the call from `call.endedReason` type: array items: type: object enabled: type: boolean description: >- This determines whether structured data is generated and stored in `call.analysis.structuredData`. Defaults to false. Usage: - If you want to extract structured data, set this to true and provide a `schema`. @default false schema: description: >- This is the schema of the structured data. The output is stored in `call.analysis.structuredData`. Complete guide on JSON Schema can be found [here](https://ajv.js.org/json-schema.html#json-data-type). allOf: - $ref: '#/components/schemas/JsonSchema' timeoutSeconds: type: number description: >- This is how long the request is tried before giving up. When request times out, `call.analysis.structuredData` will be empty. Usage: - To guarantee the structured data is generated, set this value high. Note, this will delay the end of call report in cases where model is slow to respond. @default 5 seconds minimum: 1 maximum: 60 StructuredDataMultiPlan: type: object properties: key: type: string description: This is the key of the structured data plan in the catalog. plan: description: This is an individual structured data plan in the catalog. allOf: - $ref: '#/components/schemas/StructuredDataPlan' required: - key - plan SuccessEvaluationPlan: type: object properties: rubric: type: string enum: - NumericScale - DescriptiveScale - Checklist - Matrix - PercentageScale - LikertScale - AutomaticRubric - PassFail description: >- This enforces the rubric of the evaluation. The output is stored in `call.analysis.successEvaluation`. Options include: - 'NumericScale': A scale of 1 to 10. - 'DescriptiveScale': A scale of Excellent, Good, Fair, Poor. - 'Checklist': A checklist of criteria and their status. - 'Matrix': A grid that evaluates multiple criteria across different performance levels. - 'PercentageScale': A scale of 0% to 100%. - 'LikertScale': A scale of Strongly Agree, Agree, Neutral, Disagree, Strongly Disagree. - 'AutomaticRubric': Automatically break down evaluation into several criteria, each with its own score. - 'PassFail': A simple 'true' if call passed, 'false' if not. Default is 'PassFail'. messages: description: >- These are the messages used to generate the success evaluation. @default: ``` [ { "role": "system", "content": "You are an expert call evaluator. You will be given a transcript of a call and the system prompt of the AI participant. Determine if the call was successful based on the objectives inferred from the system prompt. DO NOT return anything except the result.\n\nRubric:\\n{{rubric}}\n\nOnly respond with the result." }, { "role": "user", "content": "Here is the transcript:\n\n{{transcript}}\n\n" }, { "role": "user", "content": "Here was the system prompt of the call:\n\n{{systemPrompt}}\n\n. Here is the ended reason of the call:\n\n{{endedReason}}\n\n" } ]``` You can customize by providing any messages you want. Here are the template variables available: - {{transcript}}: the transcript of the call from `call.artifact.transcript`- {{systemPrompt}}: the system prompt of the call from `assistant.model.messages[type=system].content`- {{rubric}}: the rubric of the success evaluation from `successEvaluationPlan.rubric`- {{endedReason}}: the ended reason of the call from `call.endedReason` type: array items: type: object enabled: type: boolean description: >- This determines whether a success evaluation is generated and stored in `call.analysis.successEvaluation`. Defaults to true. Usage: - If you want to disable the success evaluation, set this to false. @default true timeoutSeconds: type: number description: >- This is how long the request is tried before giving up. When request times out, `call.analysis.successEvaluation` will be empty. Usage: - To guarantee the success evaluation is generated, set this value high. Note, this will delay the end of call report in cases where model is slow to respond. @default 5 seconds minimum: 1 maximum: 60 TranscriptPlan: type: object properties: enabled: type: boolean description: >- This determines whether the transcript is stored in `call.artifact.transcript`. Defaults to true. @default true example: true assistantName: type: string description: >- This is the name of the assistant in the transcript. Defaults to 'AI'. Usage: - If you want to change the name of the assistant in the transcript, set this. Example, here is what the transcript would look like with `assistantName` set to 'Buyer': ``` User: Hello, how are you? Buyer: I'm fine. User: Do you want to buy a car? Buyer: No. ``` @default 'AI' userName: type: string description: >- This is the name of the user in the transcript. Defaults to 'User'. Usage: - If you want to change the name of the user in the transcript, set this. Example, here is what the transcript would look like with `userName` set to 'Seller': ``` Seller: Hello, how are you? AI: I'm fine. Seller: Do you want to buy a car? AI: No. ``` @default 'User' cozmoxSmartEndpointingPlan: type: object properties: provider: type: string description: This is the provider for the smart endpointing plan. enum: - cozmox - livekit - custom-endpointing-model example: cozmox required: - provider LivekitSmartEndpointingPlan: type: object properties: provider: type: string description: This is the provider for the smart endpointing plan. enum: - cozmox - livekit - custom-endpointing-model example: livekit waitFunction: type: string description: >- This expression describes how long the bot will wait to start speaking based on the likelihood that the user has reached an endpoint. This is a millisecond valued function. It maps probabilities (real numbers on [0,1]) to milliseconds that the bot should wait before speaking ([0, \infty]). Any negative values that are returned are set to zero (the bot can't start talking in the past). A probability of zero represents very high confidence that the caller has stopped speaking, and would like the bot to speak to them. A probability of one represents very high confidence that the caller is still speaking. Under the hood, this is parsed into a mathjs expression. Whatever you use to write your expression needs to be valid with respect to mathjs @default "20 + 500 * sqrt(x) + 2500 * x^3" example: - 70 + 4000 * x - 200 + 8000 * x - 4000 * (1 - cos(pi * x)) required: - provider CustomEndpointingModelSmartEndpointingPlan: type: object properties: provider: type: string description: >- This is the provider for the smart endpointing plan. Use `custom-endpointing-model` for custom endpointing providers that are not natively supported. enum: - cozmox - livekit - custom-endpointing-model example: custom-endpointing-model server: description: >- This is where the endpointing request will be sent. If not provided, will be sent to `assistant.server`. If that does not exist either, will be sent to `org.server`. Request Example: POST https://{server.url} Content-Type: application/json { "message": { "type": "call.endpointing.request", "messages": [ { "role": "user", "message": "Hello, how are you?", "time": 1234567890, "secondsFromStart": 0 } ], ...other metadata about the call... } } Response Expected: { "timeoutSeconds": 0.5 } The timeout is the number of seconds to wait before considering the user's speech as finished. The endpointing timeout is automatically reset each time a new transcript is received (and another `call.endpointing.request` is sent). allOf: - $ref: '#/components/schemas/Server' required: - provider AssistantCustomEndpointingRule: type: object properties: type: type: string description: >- This endpointing rule is based on the last assistant message before customer started speaking. Flow: - Assistant speaks - Customer starts speaking - Customer transcription comes in - This rule is evaluated on the last assistant message - If a match is found based on `regex`, the endpointing timeout is set to `timeoutSeconds` Usage: - If you have yes/no questions in your use case like "are you interested in a loan?", you can set a shorter timeout. - If you have questions where the customer may pause to look up information like "what's my account number?", you can set a longer timeout. enum: - assistant regex: type: string description: >- This is the regex pattern to match. Note: - This works by using the `RegExp.test` method in Node.JS. Eg. `/hello/.test("hello there")` will return `true`. Hot tip: - In JavaScript, escape `\` when sending the regex pattern. Eg. `"hello\sthere"` will be sent over the wire as `"hellosthere"`. Send `"hello\\sthere"` instead. - `RegExp.test` does substring matching, so `/cat/.test("I love cats")` will return `true`. To do full string matching, send "^cat$". regexOptions: description: |- These are the options for the regex match. Defaults to all disabled. @default [] type: array items: $ref: '#/components/schemas/RegexOption' timeoutSeconds: type: number description: This is the endpointing timeout in seconds, if the rule is matched. minimum: 0 maximum: 15 required: - type - regex - timeoutSeconds CustomerCustomEndpointingRule: type: object properties: type: type: string description: >- This endpointing rule is based on current customer message as they are speaking. Flow: - Assistant speaks - Customer starts speaking - Customer transcription comes in - This rule is evaluated on the current customer transcription - If a match is found based on `regex`, the endpointing timeout is set to `timeoutSeconds` Usage: - If you want to wait longer while customer is speaking numbers, you can set a longer timeout. enum: - customer regex: type: string description: >- This is the regex pattern to match. Note: - This works by using the `RegExp.test` method in Node.JS. Eg. `/hello/.test("hello there")` will return `true`. Hot tip: - In JavaScript, escape `\` when sending the regex pattern. Eg. `"hello\sthere"` will be sent over the wire as `"hellosthere"`. Send `"hello\\sthere"` instead. - `RegExp.test` does substring matching, so `/cat/.test("I love cats")` will return `true`. To do full string matching, send "^cat$". regexOptions: description: |- These are the options for the regex match. Defaults to all disabled. @default [] type: array items: $ref: '#/components/schemas/RegexOption' timeoutSeconds: type: number description: This is the endpointing timeout in seconds, if the rule is matched. minimum: 0 maximum: 15 required: - type - regex - timeoutSeconds BothCustomEndpointingRule: type: object properties: type: type: string description: >- This endpointing rule is based on both the last assistant message and the current customer message as they are speaking. Flow: - Assistant speaks - Customer starts speaking - Customer transcription comes in - This rule is evaluated on the last assistant message and the current customer transcription - If assistant message matches `assistantRegex` AND customer message matches `customerRegex`, the endpointing timeout is set to `timeoutSeconds` Usage: - If you want to wait longer while customer is speaking numbers, you can set a longer timeout. enum: - both assistantRegex: type: string description: >- This is the regex pattern to match the assistant's message. Note: - This works by using the `RegExp.test` method in Node.JS. Eg. `/hello/.test("hello there")` will return `true`. Hot tip: - In JavaScript, escape `\` when sending the regex pattern. Eg. `"hello\sthere"` will be sent over the wire as `"hellosthere"`. Send `"hello\\sthere"` instead. - `RegExp.test` does substring matching, so `/cat/.test("I love cats")` will return `true`. To do full string matching, send "^cat$". assistantRegexOptions: description: >- These are the options for the assistant's message regex match. Defaults to all disabled. @default [] type: array items: $ref: '#/components/schemas/RegexOption' customerRegex: type: string customerRegexOptions: description: >- These are the options for the customer's message regex match. Defaults to all disabled. @default [] type: array items: $ref: '#/components/schemas/RegexOption' timeoutSeconds: type: number description: This is the endpointing timeout in seconds, if the rule is matched. minimum: 0 maximum: 15 required: - type - assistantRegex - customerRegex - timeoutSeconds TranscriptionEndpointingPlan: type: object properties: onPunctuationSeconds: type: number description: >- The minimum number of seconds to wait after transcription ending with punctuation before sending a request to the model. Defaults to 0.1. This setting exists because the transcriber punctuates the transcription when it's more confident that customer has completed a thought. @default 0.1 minimum: 0 maximum: 3 example: 0.1 onNoPunctuationSeconds: type: number description: >- The minimum number of seconds to wait after transcription ending without punctuation before sending a request to the model. Defaults to 1.5. This setting exists to catch the cases where the transcriber was not confident enough to punctuate the transcription, but the customer is done and has been silent for a long time. @default 1.5 minimum: 0 maximum: 3 example: 1.5 onNumberSeconds: type: number description: >- The minimum number of seconds to wait after transcription ending with a number before sending a request to the model. Defaults to 0.4. This setting exists because the transcriber will sometimes punctuate the transcription ending with a number, even though the customer hasn't uttered the full number. This happens commonly for long numbers when the customer reads the number in chunks. @default 0.5 minimum: 0 maximum: 3 example: 0.5 BackoffPlan: type: object properties: type: type: object description: |- This is the type of backoff plan to use. Defaults to fixed. @default fixed enum: - fixed - exponential example: fixed maxRetries: type: number description: >- This is the maximum number of retries to attempt if the request fails. Defaults to 0 (no retries). @default 0 minimum: 0 maximum: 10 example: 0 baseDelaySeconds: type: number description: >- This is the base delay in seconds. For linear backoff, this is the delay between each retry. For exponential backoff, this is the initial delay. minimum: 0 maximum: 10 example: 1 required: - type - maxRetries - baseDelaySeconds FallbackAssemblyAITranscriber: type: object properties: provider: type: string description: This is the transcription provider that will be used. enum: - assembly-ai language: type: string description: This is the language that will be set for the transcription. enum: - en confidenceThreshold: type: number description: |- Transcripts below this confidence threshold will be discarded. @default 0.4 minimum: 0 maximum: 1 example: 0.4 enableUniversalStreamingApi: type: boolean description: >- Uses Assembly AI's new Universal Streaming API. See: https://www.assemblyai.com/docs/speech-to-text/universal-streaming @default false example: false formatTurns: type: boolean description: >- This enables formatting of transcripts. Only used when `enableUniversalStreamingApi` is true. @default false example: false endOfTurnConfidenceThreshold: type: number description: >- The confidence threshold to use when determining if the end of a turn has been reached. Only used when `enableUniversalStreamingApi` is true. @default 0.7 minimum: 0 maximum: 1 example: 0.7 minEndOfTurnSilenceWhenConfident: type: number description: >- The minimum amount of silence in milliseconds required to detect end of turn when confident. Only used when `enableUniversalStreamingApi` is true. @default 160 minimum: 0 example: 160 wordFinalizationMaxWaitTime: type: number description: >- The maximum wait time for word finalization. Only used when `enableUniversalStreamingApi` is true. @default 160 minimum: 0 example: 160 maxTurnSilence: type: number description: >- The maximum amount of silence in milliseconds allowed in a turn before end of turn is triggered. Only used when `enableUniversalStreamingApi` is true. @default 400 minimum: 0 example: 400 realtimeUrl: type: string description: The WebSocket URL that the transcriber connects to. wordBoost: description: Add up to 2500 characters of custom vocabulary. type: array items: type: string maxLength: 2500 endUtteranceSilenceThreshold: type: number description: The duration of the end utterance silence threshold in milliseconds. disablePartialTranscripts: type: boolean description: >- Disable partial transcripts. Set to `true` to not receive partial transcripts. Defaults to `false`. required: - provider FallbackAzureSpeechTranscriber: type: object properties: provider: type: string description: This is the transcription provider that will be used. enum: - azure language: type: string description: >- This is the language that will be set for the transcription. The list of languages Azure supports can be found here: https://learn.microsoft.com/en-us/azure/ai-services/speech-service/language-support?tabs=stt enum: - af-ZA - am-ET - ar-AE - ar-BH - ar-DZ - ar-EG - ar-IL - ar-IQ - ar-JO - ar-KW - ar-LB - ar-LY - ar-MA - ar-OM - ar-PS - ar-QA - ar-SA - ar-SY - ar-TN - ar-YE - az-AZ - bg-BG - bn-IN - bs-BA - ca-ES - cs-CZ - cy-GB - da-DK - de-AT - de-CH - de-DE - el-GR - en-AU - en-CA - en-GB - en-GH - en-HK - en-IE - en-IN - en-KE - en-NG - en-NZ - en-PH - en-SG - en-TZ - en-US - en-ZA - es-AR - es-BO - es-CL - es-CO - es-CR - es-CU - es-DO - es-EC - es-ES - es-GQ - es-GT - es-HN - es-MX - es-NI - es-PA - es-PE - es-PR - es-PY - es-SV - es-US - es-UY - es-VE - et-EE - eu-ES - fa-IR - fi-FI - fil-PH - fr-BE - fr-CA - fr-CH - fr-FR - ga-IE - gl-ES - gu-IN - he-IL - hi-IN - hr-HR - hu-HU - hy-AM - id-ID - is-IS - it-CH - it-IT - ja-JP - jv-ID - ka-GE - kk-KZ - km-KH - kn-IN - ko-KR - lo-LA - lt-LT - lv-LV - mk-MK - ml-IN - mn-MN - mr-IN - ms-MY - mt-MT - my-MM - nb-NO - ne-NP - nl-BE - nl-NL - pa-IN - pl-PL - ps-AF - pt-BR - pt-PT - ro-RO - ru-RU - si-LK - sk-SK - sl-SI - so-SO - sq-AL - sr-RS - sv-SE - sw-KE - sw-TZ - ta-IN - te-IN - th-TH - tr-TR - uk-UA - ur-IN - uz-UZ - vi-VN - wuu-CN - yue-CN - zh-CN - zh-CN-shandong - zh-CN-sichuan - zh-HK - zh-TW - zu-ZA required: - provider FallbackCustomTranscriber: type: object properties: provider: type: string description: >- This is the transcription provider that will be used. Use `custom-transcriber` for providers that are not natively supported. enum: - custom-transcriber server: description: >- This is where the transcription request will be sent. Usage: 1. cozmox will initiate a websocket connection with `server.url`. 2. cozmox will send an initial text frame with the sample rate. Format: ``` { "type": "start", "encoding": "linear16", // 16-bit raw PCM format "container": "raw", "sampleRate": {{sampleRate}}, "channels": 2 // customer is channel 0, assistant is channel 1 } ``` 3. cozmox will send the audio data in 16-bit raw PCM format as binary frames. 4. You can read the messages something like this: ``` ws.on('message', (data, isBinary) => { if (isBinary) { pcmBuffer = Buffer.concat([pcmBuffer, data]); console.log(`Received PCM data, buffer size: ${pcmBuffer.length}`); } else { console.log('Received message:', JSON.parse(data.toString())); } }); ``` 5. You will respond with transcriptions as you have them. Format: ``` { "type": "transcriber-response", "transcription": "Hello, world!", "channel": "customer" | "assistant" } ``` allOf: - $ref: '#/components/schemas/Server' required: - provider - server FallbackDeepgramTranscriber: type: object properties: provider: type: string description: This is the transcription provider that will be used. enum: - deepgram model: description: >- This is the Deepgram model that will be used. A list of models can be found here: https://developers.deepgram.com/docs/models-languages-overview oneOf: - type: string enum: - nova-3 - nova-3-general - nova-3-medical - nova-2 - nova-2-general - nova-2-meeting - nova-2-phonecall - nova-2-finance - nova-2-conversationalai - nova-2-voicemail - nova-2-video - nova-2-medical - nova-2-drivethru - nova-2-automotive - nova - nova-general - nova-phonecall - nova-medical - enhanced - enhanced-general - enhanced-meeting - enhanced-phonecall - enhanced-finance - base - base-general - base-meeting - base-phonecall - base-finance - base-conversationalai - base-voicemail - base-video - whisper - type: string language: type: string description: >- This is the language that will be set for the transcription. The list of languages Deepgram supports can be found here: https://developers.deepgram.com/docs/models-languages-overview enum: - ar - az - ba - bg - br - ca - cs - da - da-DK - de - de-CH - el - en - en-AU - en-GB - en-IN - en-NZ - en-US - es - es-419 - es-LATAM - et - eu - fi - fr - fr-CA - ha - haw - he - hi - hi-Latn - hu - id - is - it - ja - jw - kn - ko - ko-KR - ln - lt - lv - mk - ms - multi - nl - nl-BE - 'no' - pl - pt - pt-BR - ro - ru - sk - sl - sn - so - sr - su - sv - sv-SE - ta - taq - th - th-TH - tr - tt - uk - ur - vi - yo - zh - zh-CN - zh-HK - zh-Hans - zh-Hant - zh-TW smartFormat: type: boolean description: >- This will be use smart format option provided by Deepgram. It's default disabled because it can sometimes format numbers as times but it's getting better. example: false mipOptOut: type: boolean description: >- If set to true, this will add mip_opt_out=true as a query parameter of all API requests. See https://developers.deepgram.com/docs/the-deepgram-model-improvement-partnership-program#want-to-opt-out This will only be used if you are using your own Deepgram API key. @default false example: false default: false numerals: type: boolean description: >- If set to true, this will cause deepgram to convert spoken numbers to literal numerals. For example, "my phone number is nine-seven-two..." would become "my phone number is 972..." @default false example: false confidenceThreshold: type: number description: |- Transcripts below this confidence threshold will be discarded. @default 0.4 minimum: 0 maximum: 1 example: 0.4 keywords: description: >- These keywords are passed to the transcription model to help it pick up use-case specific words. Anything that may not be a common word, like your company name, should be added here. type: array items: type: string pattern: /^\p{L}[\p{L}\d]*(?::[+-]?\d+)?$/u keyterm: description: >- Keyterm Prompting allows you improve Keyword Recall Rate (KRR) for important keyterms or phrases up to 90%. type: array items: type: string endpointing: type: number description: >- This is the timeout after which Deepgram will send transcription on user silence. You can read in-depth documentation here: https://developers.deepgram.com/docs/endpointing. Here are the most important bits: - Defaults to 10. This is recommended for most use cases to optimize for latency. - 10 can cause some missing transcriptions since because of the shorter context. This mostly happens for one-word utterances. For those uses cases, it's recommended to try 300. It will add a bit of latency but the quality and reliability of the experience will be better. - If neither 10 nor 300 work, contact support@cozmox.ai and we'll find another solution. @default 10 minimum: 10 maximum: 500 required: - provider FallbackElevenLabsTranscriber: type: object properties: provider: type: string description: This is the transcription provider that will be used. enum: - 11labs model: type: string description: This is the model that will be used for the transcription. enum: - scribe_v1 language: type: string enum: - aa - ab - ae - af - ak - am - an - ar - as - av - ay - az - ba - be - bg - bh - bi - bm - bn - bo - br - bs - ca - ce - ch - co - cr - cs - cu - cv - cy - da - de - dv - dz - ee - el - en - eo - es - et - eu - fa - ff - fi - fj - fo - fr - fy - ga - gd - gl - gn - gu - gv - ha - he - hi - ho - hr - ht - hu - hy - hz - ia - id - ie - ig - ii - ik - io - is - it - iu - ja - jv - ka - kg - ki - kj - kk - kl - km - kn - ko - kr - ks - ku - kv - kw - ky - la - lb - lg - li - ln - lo - lt - lu - lv - mg - mh - mi - mk - ml - mn - mr - ms - mt - my - na - nb - nd - ne - ng - nl - nn - 'no' - nr - nv - ny - oc - oj - om - or - os - pa - pi - pl - ps - pt - qu - rm - rn - ro - ru - rw - sa - sc - sd - se - sg - si - sk - sl - sm - sn - so - sq - sr - ss - st - su - sv - sw - ta - te - tg - th - ti - tk - tl - tn - to - tr - ts - tt - tw - ty - ug - uk - ur - uz - ve - vi - vo - wa - wo - xh - yi - yue - yo - za - zh - zu required: - provider FallbackGladiaTranscriber: type: object properties: provider: type: string description: This is the transcription provider that will be used. enum: - gladia model: description: This is the Gladia model that will be used. Default is 'fast' oneOf: - enum: - fast - accurate - solaria-1 languageBehaviour: description: >- Defines how the transcription model detects the audio language. Default value is 'automatic single language'. oneOf: - type: string enum: - manual - automatic single language - automatic multiple languages language: type: string description: >- Defines the language to use for the transcription. Required when languageBehaviour is 'manual'. enum: - af - sq - am - ar - hy - as - az - ba - eu - be - bn - bs - br - bg - ca - zh - hr - cs - da - nl - en - et - fo - fi - fr - gl - ka - de - el - gu - ht - ha - haw - he - hi - hu - is - id - it - ja - jv - kn - kk - km - ko - lo - la - lv - ln - lt - lb - mk - mg - ms - ml - mt - mi - mr - mn - my - ne - 'no' - nn - oc - ps - fa - pl - pt - pa - ro - ru - sa - sr - sn - sd - si - sk - sl - so - es - su - sw - sv - tl - tg - ta - tt - te - th - bo - tr - tk - uk - ur - uz - vi - cy - yi - yo languages: type: string description: >- Defines the languages to use for the transcription. Required when languageBehaviour is 'manual'. enum: - af - sq - am - ar - hy - as - az - ba - eu - be - bn - bs - br - bg - ca - zh - hr - cs - da - nl - en - et - fo - fi - fr - gl - ka - de - el - gu - ht - ha - haw - he - hi - hu - is - id - it - ja - jv - kn - kk - km - ko - lo - la - lv - ln - lt - lb - mk - mg - ms - ml - mt - mi - mr - mn - my - ne - 'no' - nn - oc - ps - fa - pl - pt - pa - ro - ru - sa - sr - sn - sd - si - sk - sl - so - es - su - sw - sv - tl - tg - ta - tt - te - th - bo - tr - tk - uk - ur - uz - vi - cy - yi - yo transcriptionHint: type: string description: >- Provides a custom vocabulary to the model to improve accuracy of transcribing context specific words, technical terms, names, etc. If empty, this argument is ignored. ⚠️ Warning ⚠️: Please be aware that the transcription_hint field has a character limit of 600. If you provide a transcription_hint longer than 600 characters, it will be automatically truncated to meet this limit. maxLength: 600 example: custom vocabulary prosody: type: boolean description: >- If prosody is true, you will get a transcription that can contain prosodies i.e. (laugh) (giggles) (malefic laugh) (toss) (music)… Default value is false. example: false audioEnhancer: type: boolean description: >- If true, audio will be pre-processed to improve accuracy but latency will increase. Default value is false. example: false confidenceThreshold: type: number description: |- Transcripts below this confidence threshold will be discarded. @default 0.4 minimum: 0 maximum: 1 example: 0.4 required: - provider FallbackGoogleTranscriber: type: object properties: provider: type: string description: This is the transcription provider that will be used. enum: - google model: type: string description: This is the model that will be used for the transcription. enum: - gemini-2.5-pro - gemini-2.5-flash - gemini-2.5-flash-lite - gemini-2.5-pro-preview-05-06 - gemini-2.5-flash-preview-05-20 - gemini-2.5-flash-preview-04-17 - gemini-2.0-flash-thinking-exp - gemini-2.0-pro-exp-02-05 - gemini-2.0-flash - gemini-2.0-flash-lite - gemini-2.0-flash-lite-preview-02-05 - gemini-2.0-flash-exp - gemini-2.0-flash-realtime-exp - gemini-1.5-flash - gemini-1.5-flash-002 - gemini-1.5-pro - gemini-1.5-pro-002 - gemini-1.0-pro language: type: string description: This is the language that will be set for the transcription. enum: - Multilingual - Arabic - Bengali - Bulgarian - Chinese - Croatian - Czech - Danish - Dutch - English - Estonian - Finnish - French - German - Greek - Hebrew - Hindi - Hungarian - Indonesian - Italian - Japanese - Korean - Latvian - Lithuanian - Norwegian - Polish - Portuguese - Romanian - Russian - Serbian - Slovak - Slovenian - Spanish - Swahili - Swedish - Thai - Turkish - Ukrainian - Vietnamese required: - provider FallbackTalkscriberTranscriber: type: object properties: provider: type: string description: This is the transcription provider that will be used. enum: - talkscriber model: type: string description: This is the model that will be used for the transcription. enum: - whisper language: type: string description: >- This is the language that will be set for the transcription. The list of languages Whisper supports can be found here: https://github.com/openai/whisper/blob/main/whisper/tokenizer.py enum: - en - zh - de - es - ru - ko - fr - ja - pt - tr - pl - ca - nl - ar - sv - it - id - hi - fi - vi - he - uk - el - ms - cs - ro - da - hu - ta - 'no' - th - ur - hr - bg - lt - la - mi - ml - cy - sk - te - fa - lv - bn - sr - az - sl - kn - et - mk - br - eu - is - hy - ne - mn - bs - kk - sq - sw - gl - mr - pa - si - km - sn - yo - so - af - oc - ka - be - tg - sd - gu - am - yi - lo - uz - fo - ht - ps - tk - nn - mt - sa - lb - my - bo - tl - mg - as - tt - haw - ln - ha - ba - jw - su - yue required: - provider FallbackSpeechmaticsTranscriber: type: object properties: provider: type: string description: This is the transcription provider that will be used. enum: - speechmatics model: type: string description: This is the model that will be used for the transcription. enum: - default language: type: string enum: - auto - ar - ba - eu - be - bn - bg - yue - ca - hr - cs - da - nl - en - eo - et - fi - fr - gl - de - el - he - hi - hu - id - ia - ga - it - ja - ko - lv - lt - ms - mt - cmn - mr - mn - 'no' - fa - pl - pt - ro - ru - sk - sl - es - sw - sv - ta - th - tr - uk - ur - ug - vi - cy required: - provider FallbackOpenAITranscriber: type: object properties: provider: type: string description: This is the transcription provider that will be used. enum: - openai model: type: string description: This is the model that will be used for the transcription. enum: - gpt-4o-transcribe - gpt-4o-mini-transcribe language: type: string description: This is the language that will be set for the transcription. enum: - af - ar - hy - az - be - bs - bg - ca - zh - hr - cs - da - nl - en - et - fi - fr - gl - de - el - he - hi - hu - is - id - it - ja - kn - kk - ko - lv - lt - mk - ms - mr - mi - ne - 'no' - fa - pl - pt - ro - ru - sr - sk - sl - es - sw - sv - tl - ta - th - tr - uk - ur - vi - cy required: - provider - model FallbackCartesiaTranscriber: type: object properties: provider: type: string enum: - cartesia model: type: string enum: - ink-whisper language: type: string enum: - aa - ab - ae - af - ak - am - an - ar - as - av - ay - az - ba - be - bg - bh - bi - bm - bn - bo - br - bs - ca - ce - ch - co - cr - cs - cu - cv - cy - da - de - dv - dz - ee - el - en - eo - es - et - eu - fa - ff - fi - fj - fo - fr - fy - ga - gd - gl - gn - gu - gv - ha - he - hi - ho - hr - ht - hu - hy - hz - ia - id - ie - ig - ii - ik - io - is - it - iu - ja - jv - ka - kg - ki - kj - kk - kl - km - kn - ko - kr - ks - ku - kv - kw - ky - la - lb - lg - li - ln - lo - lt - lu - lv - mg - mh - mi - mk - ml - mn - mr - ms - mt - my - na - nb - nd - ne - ng - nl - nn - 'no' - nr - nv - ny - oc - oj - om - or - os - pa - pi - pl - ps - pt - qu - rm - rn - ro - ru - rw - sa - sc - sd - se - sg - si - sk - sl - sm - sn - so - sq - sr - ss - st - su - sv - sw - ta - te - tg - th - ti - tk - tl - tn - to - tr - ts - tt - tw - ty - ug - uk - ur - uz - ve - vi - vo - wa - wo - xh - yi - yue - yo - za - zh - zu required: - provider ToolMessageStart: type: object properties: contents: type: array description: >- This is an alternative to the `content` property. It allows to specify variants of the same content, one per language. Usage: - If your assistants are multilingual, you can provide content for each language. - If you don't provide content for a language, the first item in the array will be automatically translated to the active language at that moment. This will override the `content` property. items: oneOf: - $ref: '#/components/schemas/TextContent' title: Text type: type: string enum: - request-start description: >- This message is triggered when the tool call starts. This message is never triggered for async tools. If this message is not provided, one of the default filler messages "Hold on a sec", "One moment", "Just a sec", "Give me a moment" or "This'll just take a sec" will be used. blocking: type: boolean description: >- This is an optional boolean that if true, the tool call will only trigger after the message is spoken. Default is false. @default false example: false default: false content: type: string description: >- This is the content that the assistant says when this message is triggered. maxLength: 1000 conditions: description: >- This is an optional array of conditions that the tool call arguments must meet in order for this message to be triggered. type: array items: $ref: '#/components/schemas/Condition' required: - type ToolMessageComplete: type: object properties: contents: type: array description: >- This is an alternative to the `content` property. It allows to specify variants of the same content, one per language. Usage: - If your assistants are multilingual, you can provide content for each language. - If you don't provide content for a language, the first item in the array will be automatically translated to the active language at that moment. This will override the `content` property. items: oneOf: - $ref: '#/components/schemas/TextContent' title: Text type: type: string description: >- This message is triggered when the tool call is complete. This message is triggered immediately without waiting for your server to respond for async tool calls. If this message is not provided, the model will be requested to respond. If this message is provided, only this message will be spoken and the model will not be requested to come up with a response. It's an exclusive OR. enum: - request-complete role: type: string description: >- This is optional and defaults to "assistant". When role=assistant, `content` is said out loud. When role=system, `content` is passed to the model in a system message. Example: system: default one assistant: user: assistant: user: assistant: user: assistant: tool called tool: your server response <--- system prompt as hint ---> model generates response which is spoken This is useful when you want to provide a hint to the model about what to say next. enum: - assistant - system endCallAfterSpokenEnabled: type: boolean description: >- This is an optional boolean that if true, the call will end after the message is spoken. Default is false. This is ignored if `role` is set to `system`. @default false example: false content: type: string description: >- This is the content that the assistant says when this message is triggered. maxLength: 1000 conditions: description: >- This is an optional array of conditions that the tool call arguments must meet in order for this message to be triggered. type: array items: $ref: '#/components/schemas/Condition' required: - type ToolMessageFailed: type: object properties: contents: type: array description: >- This is an alternative to the `content` property. It allows to specify variants of the same content, one per language. Usage: - If your assistants are multilingual, you can provide content for each language. - If you don't provide content for a language, the first item in the array will be automatically translated to the active language at that moment. This will override the `content` property. items: oneOf: - $ref: '#/components/schemas/TextContent' title: Text type: type: string description: >- This message is triggered when the tool call fails. This message is never triggered for async tool calls. If this message is not provided, the model will be requested to respond. If this message is provided, only this message will be spoken and the model will not be requested to come up with a response. It's an exclusive OR. enum: - request-failed endCallAfterSpokenEnabled: type: boolean description: >- This is an optional boolean that if true, the call will end after the message is spoken. Default is false. @default false example: false content: type: string description: >- This is the content that the assistant says when this message is triggered. maxLength: 1000 conditions: description: >- This is an optional array of conditions that the tool call arguments must meet in order for this message to be triggered. type: array items: $ref: '#/components/schemas/Condition' required: - type ToolMessageDelayed: type: object properties: contents: type: array description: >- This is an alternative to the `content` property. It allows to specify variants of the same content, one per language. Usage: - If your assistants are multilingual, you can provide content for each language. - If you don't provide content for a language, the first item in the array will be automatically translated to the active language at that moment. This will override the `content` property. items: oneOf: - $ref: '#/components/schemas/TextContent' title: Text type: type: string description: >- This message is triggered when the tool call is delayed. There are the two things that can trigger this message: 1. The user talks with the assistant while your server is processing the request. Default is "Sorry, a few more seconds." 2. The server doesn't respond within `timingMilliseconds`. This message is never triggered for async tool calls. enum: - request-response-delayed timingMilliseconds: type: number minimum: 100 maximum: 120000 example: 1000 description: >- The number of milliseconds to wait for the server response before saying this message. content: type: string description: >- This is the content that the assistant says when this message is triggered. maxLength: 1000 conditions: description: >- This is an optional array of conditions that the tool call arguments must meet in order for this message to be triggered. type: array items: $ref: '#/components/schemas/Condition' required: - type JsonSchema: type: object properties: type: type: string description: >- This is the type of output you'd like. `string`, `number`, `integer`, `boolean` are the primitive types and should be obvious. `array` and `object` are more interesting and quite powerful. They allow you to define nested structures. For `array`, you can define the schema of the items in the array using the `items` property. For `object`, you can define the properties of the object using the `properties` property. enum: - string - number - integer - boolean - array - object items: type: object description: >- This is required if the type is "array". This is the schema of the items in the array. This is of type JsonSchema. However, Swagger doesn't support circular references. properties: type: object description: >- This is required if the type is "object". This specifies the properties of the object. This is a map of string to JsonSchema. However, Swagger doesn't support circular references. description: type: string description: >- This is the description to help the model understand what it needs to output. pattern: type: string description: >- This is the pattern of the string. This is a regex that will be used to validate the data in question. To use a common format, use the `format` property instead. OpenAI documentation: https://platform.openai.com/docs/guides/structured-outputs#supported-properties format: type: string description: >- This is the format of the string. To pass a regex, use the `pattern` property instead. OpenAI documentation: https://platform.openai.com/docs/guides/structured-outputs?api-mode=chat&type-restrictions=string-restrictions enum: - date-time - time - date - duration - email - hostname - ipv4 - ipv6 - uuid required: description: |- This is a list of properties that are required. This only makes sense if the type is "object". type: array items: type: string enum: description: >- This array specifies the allowed values that can be used to restrict the output of the model. type: array items: type: string title: type: string description: This is the title of the schema. required: - type VariableExtractionPlan: type: object properties: schema: description: >- This is the schema to extract. Examples: 1. To extract object properties, you can use the following schema: ```json { "type": "object", "properties": { "name": { "type": "string" }, "age": { "type": "number" } } } ``` These will be extracted as `{{ name }}` and `{{ age }}` respectively. To emphasize, object properties are extracted as direct global variables. 2. To extract nested properties, you can use the following schema: ```json { "type": "object", "properties": { "name": { "type": "object", "properties": { "first": { "type": "string" }, "last": { "type": "string" } } } } } ``` These will be extracted as `{{ name }}`. And, `{{ name.first }}` and `{{ name.last }}` will be accessible. 3. To extract array items, you can use the following schema: ```json { "type": "array", "title": "zipCodes", "items": { "type": "string" } } ``` This will be extracted as `{{ zipCodes }}`. To access the array items, you can use `{{ zipCodes[0] }}` and `{{ zipCodes[1] }}`. 4. To extract array of objects, you can use the following schema: ```json { "type": "array", "name": "people", "items": { "type": "object", "properties": { "name": { "type": "string" }, "age": { "type": "number" }, "zipCodes": { "type": "array", "items": { "type": "string" } } } } } ``` This will be extracted as `{{ people }}`. To access the array items, you can use `{{ people[n].name }}`, `{{ people[n].age }}`, `{{ people[n].zipCodes }}`, `{{ people[n].zipCodes[0] }}` and `{{ people[n].zipCodes[1] }}`. allOf: - $ref: '#/components/schemas/JsonSchema' aliases: description: >- These are additional variables to create. These will be accessible during the call as `{{key}}` and stored in `call.artifact.variableValues` after the call. Example: ```json { "aliases": [ { "key": "customerName", "value": "{{name}}" }, { "key": "fullName", "value": "{{firstName}} {{lastName}}" }, { "key": "greeting", "value": "Hello {{name}}, welcome to {{company}}!" }, { "key": "customerEmail", "value": "{{addresses[0].city}}" }, { "key": "something", "value": "{{any liquid}}" } ] } ``` This will create variables `customerName`, `fullName`, `customerEmail`, `greeting`, and `something`. To access these variables, you can reference them as `{{customerName}}`, `{{fullName}}`, `{{customerEmail}}`, `{{greeting}}`, and `{{something}}`. type: array items: $ref: '#/components/schemas/VariableExtractionAlias' OpenAIFunction: type: object properties: strict: type: boolean description: >- This is a boolean that controls whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the [OpenAI guide](https://openai.com/index/introducing-structured-outputs-in-the-api/). @default false default: false name: type: string description: >- This is the the name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64. maxLength: 64 pattern: /^[a-zA-Z0-9_-]{1,64}$/ description: type: string description: >- This is the description of what the function does, used by the AI to choose when and how to call the function. maxLength: 1000 parameters: description: >- These are the parameters the functions accepts, described as a JSON Schema object. See the [OpenAI guide](https://platform.openai.com/docs/guides/function-calling) for examples, and the [JSON Schema reference](https://json-schema.org/understanding-json-schema) for documentation about the format. Omitting parameters defines a function with an empty parameter list. allOf: - $ref: '#/components/schemas/OpenAIFunctionParameters' required: - name McpToolMetadata: type: object properties: protocol: type: string enum: - sse - shttp description: >- This is the protocol used for MCP communication. Defaults to Streamable HTTP. KnowledgeBase: type: object properties: name: type: string description: The name of the knowledge base example: My Knowledge Base provider: type: string description: The provider of the knowledge base enum: - google example: google model: type: string description: The model to use for the knowledge base enum: - gemini-2.5-pro - gemini-2.5-flash - gemini-2.5-flash-lite - gemini-2.5-pro-preview-05-06 - gemini-2.5-flash-preview-05-20 - gemini-2.5-flash-preview-04-17 - gemini-2.0-flash-thinking-exp - gemini-2.0-pro-exp-02-05 - gemini-2.0-flash - gemini-2.0-flash-lite - gemini-2.0-flash-lite-preview-02-05 - gemini-2.0-flash-exp - gemini-2.0-flash-realtime-exp - gemini-1.5-flash - gemini-1.5-flash-002 - gemini-1.5-pro - gemini-1.5-pro-002 - gemini-1.0-pro description: type: string description: A description of the knowledge base fileIds: description: The file IDs associated with this knowledge base type: array items: type: string required: - name - provider - description - fileIds TransferDestinationAssistant: type: object properties: message: description: >- This is spoken to the customer before connecting them to the destination. Usage: - If this is not provided and transfer tool messages is not provided, default is "Transferring the call now". - If set to "", nothing is spoken. This is useful when you want to silently transfer. This is especially useful when transferring between assistants in a squad. In this scenario, you likely also want to set `assistant.firstMessageMode=assistant-speaks-first-with-model-generated-message` for the destination assistant. This accepts a string or a ToolMessageStart class. Latter is useful if you want to specify multiple messages for different languages through the `contents` field. oneOf: - type: string - $ref: '#/components/schemas/CustomMessage' type: type: string enum: - assistant transferMode: type: string description: >- This is the mode to use for the transfer. Defaults to `rolling-history`. - `rolling-history`: This is the default mode. It keeps the entire conversation history and appends the new assistant's system message on transfer. Example: Pre-transfer: system: assistant1 system message assistant: assistant1 first message user: hey, good morning assistant: how can i help? user: i need help with my account assistant: (destination.message) Post-transfer: system: assistant1 system message assistant: assistant1 first message user: hey, good morning assistant: how can i help? user: i need help with my account assistant: (destination.message) system: assistant2 system message assistant: assistant2 first message (or model generated if firstMessageMode is set to `assistant-speaks-first-with-model-generated-message`) - `swap-system-message-in-history`: This replaces the original system message with the new assistant's system message on transfer. Example: Pre-transfer: system: assistant1 system message assistant: assistant1 first message user: hey, good morning assistant: how can i help? user: i need help with my account assistant: (destination.message) Post-transfer: system: assistant2 system message assistant: assistant1 first message user: hey, good morning assistant: how can i help? user: i need help with my account assistant: (destination.message) assistant: assistant2 first message (or model generated if firstMessageMode is set to `assistant-speaks-first-with-model-generated-message`) - `delete-history`: This deletes the entire conversation history on transfer. Example: Pre-transfer: system: assistant1 system message assistant: assistant1 first message user: hey, good morning assistant: how can i help? user: i need help with my account assistant: (destination.message) Post-transfer: system: assistant2 system message assistant: assistant2 first message user: Yes, please assistant: how can i help? user: i need help with my account - `swap-system-message-in-history-and-remove-transfer-tool-messages`: This replaces the original system message with the new assistant's system message on transfer and removes transfer tool messages from conversation history sent to the LLM. Example: Pre-transfer: system: assistant1 system message assistant: assistant1 first message user: hey, good morning assistant: how can i help? user: i need help with my account transfer-tool transfer-tool-result assistant: (destination.message) Post-transfer: system: assistant2 system message assistant: assistant1 first message user: hey, good morning assistant: how can i help? user: i need help with my account assistant: (destination.message) assistant: assistant2 first message (or model generated if firstMessageMode is set to `assistant-speaks-first-with-model-generated-message`) @default 'rolling-history' enum: - rolling-history - swap-system-message-in-history - swap-system-message-in-history-and-remove-transfer-tool-messages - delete-history assistantName: type: string description: This is the assistant to transfer the call to. description: type: string description: >- This is the description of the destination, used by the AI to choose when and how to transfer the call. required: - type - assistantName TransferDestinationNumber: type: object properties: message: description: >- This is spoken to the customer before connecting them to the destination. Usage: - If this is not provided and transfer tool messages is not provided, default is "Transferring the call now". - If set to "", nothing is spoken. This is useful when you want to silently transfer. This is especially useful when transferring between assistants in a squad. In this scenario, you likely also want to set `assistant.firstMessageMode=assistant-speaks-first-with-model-generated-message` for the destination assistant. This accepts a string or a ToolMessageStart class. Latter is useful if you want to specify multiple messages for different languages through the `contents` field. oneOf: - type: string - $ref: '#/components/schemas/CustomMessage' type: type: string enum: - number numberE164CheckEnabled: type: boolean description: >- This is the flag to toggle the E164 check for the `number` field. This is an advanced property which should be used if you know your use case requires it. Use cases: - `false`: To allow non-E164 numbers like `+001234567890`, `1234`, or `abc`. This is useful for dialing out to non-E164 numbers on your SIP trunks. - `true` (default): To allow only E164 numbers like `+14155551234`. This is standard for PSTN calls. If `false`, the `number` is still required to only contain alphanumeric characters (regex: `/^\+?[a-zA-Z0-9]+$/`). @default true (E164 check is enabled) default: true number: type: string description: This is the phone number to transfer the call to. minLength: 3 maxLength: 40 extension: type: string description: >- This is the extension to dial after transferring the call to the `number`. minLength: 1 maxLength: 10 callerId: type: string description: >- This is the caller ID to use when transferring the call to the `number`. Usage: - If not provided, the caller ID will be the number the call is coming from. Example, +14151111111 calls in to and the assistant transfers out to +16470000000. +16470000000 will see +14151111111 as the caller. - To change this behavior, provide a `callerId`. - Set to '{{customer.number}}' to always use the customer's number as the caller ID. - Set to '{{phoneNumber.number}}' to always use the phone number of the assistant as the caller ID. - Set to any E164 number to always use that number as the caller ID. This needs to be a number that is owned or verified by your Transport provider like Twilio. For Twilio, you can read up more here: https://www.twilio.com/docs/voice/twiml/dial#callerid maxLength: 40 transferPlan: description: >- This configures how transfer is executed and the experience of the destination party receiving the call. Defaults to `blind-transfer`. @default `transferPlan.mode='blind-transfer'` allOf: - $ref: '#/components/schemas/TransferPlan' description: type: string description: >- This is the description of the destination, used by the AI to choose when and how to transfer the call. required: - type - number TransferDestinationSip: type: object properties: message: description: >- This is spoken to the customer before connecting them to the destination. Usage: - If this is not provided and transfer tool messages is not provided, default is "Transferring the call now". - If set to "", nothing is spoken. This is useful when you want to silently transfer. This is especially useful when transferring between assistants in a squad. In this scenario, you likely also want to set `assistant.firstMessageMode=assistant-speaks-first-with-model-generated-message` for the destination assistant. This accepts a string or a ToolMessageStart class. Latter is useful if you want to specify multiple messages for different languages through the `contents` field. oneOf: - type: string - $ref: '#/components/schemas/CustomMessage' type: type: string enum: - sip sipUri: type: string description: This is the SIP URI to transfer the call to. transferPlan: description: >- This configures how transfer is executed and the experience of the destination party receiving the call. Defaults to `blind-transfer`. @default `transferPlan.mode='blind-transfer'` allOf: - $ref: '#/components/schemas/TransferPlan' sipHeaders: type: object description: >- These are custom headers to be added to SIP refer during transfer call. description: type: string description: >- This is the description of the destination, used by the AI to choose when and how to transfer the call. required: - type - sipUri GeminiMultimodalLiveSpeechConfig: type: object properties: voiceConfig: $ref: '#/components/schemas/GeminiMultimodalLiveVoiceConfig' required: - voiceConfig FormatPlan: type: object properties: enabled: type: boolean description: >- This determines whether the chunk is formatted before being sent to the voice provider. This helps with enunciation. This includes phone numbers, emails and addresses. Default `true`. Usage: - To rely on the voice provider's formatting logic, set this to `false`. If `voice.chunkPlan.enabled` is `false`, this is automatically `false` since there's no chunk to format. @default true example: true numberToDigitsCutoff: type: number description: >- This is the cutoff after which a number is converted to individual digits instead of being spoken as words. Example: - If cutoff 2025, "12345" is converted to "1 2 3 4 5" while "1200" is converted to "twelve hundred". Usage: - If your use case doesn't involve IDs like zip codes, set this to a high value. - If your use case involves IDs that are shorter than 5 digits, set this to a lower value. @default 2025 minimum: 0 example: 2025 replacements: type: array description: >- These are the custom replacements you can make to the chunk before it is sent to the voice provider. Usage: - To replace a specific word or phrase with a different word or phrase, use the `ExactReplacement` type. Eg. `{ type: 'exact', key: 'hello', value: 'hi' }` - To replace a word or phrase that matches a pattern, use the `RegexReplacement` type. Eg. `{ type: 'regex', regex: '\\b[a-zA-Z]{5}\\b', value: 'hi' }` @default [] items: oneOf: - $ref: '#/components/schemas/ExactReplacement' title: ExactReplacement - $ref: '#/components/schemas/RegexReplacement' title: RegexReplacement formattersEnabled: type: array description: >- List of formatters to apply. If not provided, all default formatters will be applied. If provided, only the specified formatters will be applied. Note: Some essential formatters like angle bracket removal will always be applied. @default undefined enum: - markdown - asterisk - quote - dash - newline - colon - acronym - dollarAmount - email - date - time - distance - unit - percentage - phoneNumber - number - stripAsterisk items: type: string enum: - markdown - asterisk - quote - dash - newline - colon - acronym - dollarAmount - email - date - time - distance - unit - percentage - phoneNumber - number - stripAsterisk FallbackAzureVoice: type: object properties: cachingEnabled: type: boolean description: This is the flag to toggle voice caching for the assistant. example: true default: true provider: type: string description: This is the voice provider that will be used. enum: - azure voiceId: description: This is the provider-specific ID that will be used. oneOf: - type: string enum: - andrew - brian - emma title: Preset Voice Options - type: string title: Azure Voice ID speed: type: number description: This is the speed multiplier that will be used. minimum: 0.5 maximum: 2 chunkPlan: description: >- This is the plan for chunking the model output before it is sent to the voice provider. allOf: - $ref: '#/components/schemas/ChunkPlan' required: - provider - voiceId FallbackCartesiaVoice: type: object properties: cachingEnabled: type: boolean description: This is the flag to toggle voice caching for the assistant. example: true default: true provider: type: string description: This is the voice provider that will be used. enum: - cartesia voiceId: type: string description: The ID of the particular voice you want to use. model: type: string description: >- This is the model that will be used. This is optional and will default to the correct model for the voiceId. enum: - sonic-2 - sonic-english - sonic-multilingual - sonic-preview - sonic example: sonic-english language: type: string description: >- This is the language that will be used. This is optional and will default to the correct language for the voiceId. enum: - en - de - es - fr - ja - pt - zh - hi - it - ko - nl - pl - ru - sv - tr example: en experimentalControls: description: Experimental controls for Cartesia voice generation allOf: - $ref: '#/components/schemas/CartesiaExperimentalControls' chunkPlan: description: >- This is the plan for chunking the model output before it is sent to the voice provider. allOf: - $ref: '#/components/schemas/ChunkPlan' required: - provider - voiceId FallbackHumeVoice: type: object properties: cachingEnabled: type: boolean description: This is the flag to toggle voice caching for the assistant. example: true default: true provider: type: string description: This is the voice provider that will be used. enum: - hume model: type: string description: This is the model that will be used. enum: - octave example: octave voiceId: type: string description: The ID of the particular voice you want to use. isCustomHumeVoice: type: boolean description: >- Indicates whether the chosen voice is a preset Hume AI voice or a custom voice. example: false description: type: string description: >- Natural language instructions describing how the synthesized speech should sound, including but not limited to tone, intonation, pacing, and accent (e.g., 'a soft, gentle voice with a strong British accent'). If a Voice is specified in the request, this description serves as acting instructions. If no Voice is specified, a new voice is generated based on this description. chunkPlan: description: >- This is the plan for chunking the model output before it is sent to the voice provider. allOf: - $ref: '#/components/schemas/ChunkPlan' required: - provider - voiceId FallbackCustomVoice: type: object properties: cachingEnabled: type: boolean description: This is the flag to toggle voice caching for the assistant. example: true default: true provider: type: string description: >- This is the voice provider that will be used. Use `custom-voice` for providers that are not natively supported. enum: - custom-voice server: description: >- This is where the voice request will be sent. Request Example: POST https://{server.url} Content-Type: application/json { "message": { "type": "voice-request", "text": "Hello, world!", "sampleRate": 24000, ...other metadata about the call... } } Response Expected: 1-channel 16-bit raw PCM audio at the sample rate specified in the request. Here is how the response will be piped to the transport: ``` response.on('data', (chunk: Buffer) => { outputStream.write(chunk); }); ``` allOf: - $ref: '#/components/schemas/Server' chunkPlan: description: >- This is the plan for chunking the model output before it is sent to the voice provider. allOf: - $ref: '#/components/schemas/ChunkPlan' required: - provider - server FallbackDeepgramVoice: type: object properties: cachingEnabled: type: boolean description: This is the flag to toggle voice caching for the assistant. example: true default: true provider: type: string description: This is the voice provider that will be used. enum: - deepgram voiceId: type: string description: This is the provider-specific ID that will be used. enum: - asteria - luna - stella - athena - hera - orion - arcas - perseus - angus - orpheus - helios - zeus - thalia - andromeda - helena - apollo - arcas - aries - amalthea - asteria - athena - atlas - aurora - callista - cora - cordelia - delia - draco - electra - harmonia - hera - hermes - hyperion - iris - janus - juno - jupiter - luna - mars - minerva - neptune - odysseus - ophelia - orion - orpheus - pandora - phoebe - pluto - saturn - selene - theia - vesta - zeus title: This is the Deepgram Voice ID model: type: string description: >- This is the model that will be used. Defaults to 'aura-2' when not specified. enum: - aura - aura-2 example: aura-2 mipOptOut: type: boolean description: >- If set to true, this will add mip_opt_out=true as a query parameter of all API requests. See https://developers.deepgram.com/docs/the-deepgram-model-improvement-partnership-program#want-to-opt-out This will only be used if you are using your own Deepgram API key. @default false example: false default: false chunkPlan: description: >- This is the plan for chunking the model output before it is sent to the voice provider. allOf: - $ref: '#/components/schemas/ChunkPlan' required: - provider - voiceId FallbackElevenLabsVoice: type: object properties: cachingEnabled: type: boolean description: This is the flag to toggle voice caching for the assistant. example: true default: true provider: type: string description: This is the voice provider that will be used. enum: - 11labs voiceId: description: >- This is the provider-specific ID that will be used. Ensure the Voice is present in your 11Labs Voice Library. oneOf: - type: string enum: - burt - marissa - andrea - sarah - phillip - steve - joseph - myra - paula - ryan - drew - paul - mrb - matilda - mark title: Preset Voice Options - type: string title: 11Labs Voice ID stability: type: number description: Defines the stability for voice settings. minimum: 0 maximum: 1 example: 0.5 similarityBoost: type: number description: Defines the similarity boost for voice settings. minimum: 0 maximum: 1 example: 0.75 style: type: number description: Defines the style for voice settings. minimum: 0 maximum: 1 example: 0 useSpeakerBoost: type: boolean description: Defines the use speaker boost for voice settings. example: false speed: type: number description: Defines the speed for voice settings. minimum: 0.7 maximum: 1.2 example: 0.9 optimizeStreamingLatency: type: number description: >- Defines the optimize streaming latency for voice settings. Defaults to 3. minimum: 0 maximum: 4 example: 3 enableSsmlParsing: type: boolean description: >- This enables the use of https://elevenlabs.io/docs/speech-synthesis/prompting#pronunciation. Defaults to false to save latency. @default false example: false autoMode: type: boolean description: Defines the auto mode for voice settings. Defaults to false. example: false model: type: string description: >- This is the model that will be used. Defaults to 'eleven_turbo_v2' if not specified. enum: - eleven_multilingual_v2 - eleven_turbo_v2 - eleven_turbo_v2_5 - eleven_flash_v2 - eleven_flash_v2_5 - eleven_monolingual_v1 example: eleven_turbo_v2_5 language: type: string description: >- This is the language (ISO 639-1) that is enforced for the model. Currently only Turbo v2.5 supports language enforcement. For other models, an error will be returned if language code is provided. chunkPlan: description: >- This is the plan for chunking the model output before it is sent to the voice provider. allOf: - $ref: '#/components/schemas/ChunkPlan' required: - provider - voiceId FallbackcozmoxVoice: type: object properties: cachingEnabled: type: boolean description: This is the flag to toggle voice caching for the assistant. example: true default: true provider: type: string description: This is the voice provider that will be used. enum: - cozmox voiceId: type: string description: The voices provided by cozmox enum: - Elliot - Kylie - Rohan - Lily - Savannah - Hana - Neha - Cole - Harry - Paige - Spencer speed: type: number description: |- This is the speed multiplier that will be used. @default 1 minimum: 0.25 maximum: 2 default: 1 chunkPlan: description: >- This is the plan for chunking the model output before it is sent to the voice provider. allOf: - $ref: '#/components/schemas/ChunkPlan' required: - provider - voiceId FallbackLMNTVoice: type: object properties: cachingEnabled: type: boolean description: This is the flag to toggle voice caching for the assistant. example: true default: true provider: type: string description: This is the voice provider that will be used. enum: - lmnt voiceId: description: This is the provider-specific ID that will be used. oneOf: - type: string enum: - amy - ansel - autumn - ava - brandon - caleb - cassian - chloe - dalton - daniel - dustin - elowen - evander - huxley - james - juniper - kennedy - lauren - leah - lily - lucas - magnus - miles - morgan - natalie - nathan - noah - nyssa - oliver - paige - ryan - sadie - sophie - stella - terrence - tyler - vesper - violet - warrick - zain - zeke - zoe title: Preset Voice Options - type: string title: LMNT Voice ID speed: type: number description: This is the speed multiplier that will be used. minimum: 0.25 maximum: 2 example: null language: description: Two letter ISO 639-1 language code. Use "auto" for auto-detection. enum: - aa - ab - ae - af - ak - am - an - ar - as - av - ay - az - ba - be - bg - bh - bi - bm - bn - bo - br - bs - ca - ce - ch - co - cr - cs - cu - cv - cy - da - de - dv - dz - ee - el - en - eo - es - et - eu - fa - ff - fi - fj - fo - fr - fy - ga - gd - gl - gn - gu - gv - ha - he - hi - ho - hr - ht - hu - hy - hz - ia - id - ie - ig - ii - ik - io - is - it - iu - ja - jv - ka - kg - ki - kj - kk - kl - km - kn - ko - kr - ks - ku - kv - kw - ky - la - lb - lg - li - ln - lo - lt - lu - lv - mg - mh - mi - mk - ml - mn - mr - ms - mt - my - na - nb - nd - ne - ng - nl - nn - 'no' - nr - nv - ny - oc - oj - om - or - os - pa - pi - pl - ps - pt - qu - rm - rn - ro - ru - rw - sa - sc - sd - se - sg - si - sk - sl - sm - sn - so - sq - sr - ss - st - su - sv - sw - ta - te - tg - th - ti - tk - tl - tn - to - tr - ts - tt - tw - ty - ug - uk - ur - uz - ve - vi - vo - wa - wo - xh - yi - yue - yo - za - zh - zu - auto example: en oneOf: - type: string enum: - aa - ab - ae - af - ak - am - an - ar - as - av - ay - az - ba - be - bg - bh - bi - bm - bn - bo - br - bs - ca - ce - ch - co - cr - cs - cu - cv - cy - da - de - dv - dz - ee - el - en - eo - es - et - eu - fa - ff - fi - fj - fo - fr - fy - ga - gd - gl - gn - gu - gv - ha - he - hi - ho - hr - ht - hu - hy - hz - ia - id - ie - ig - ii - ik - io - is - it - iu - ja - jv - ka - kg - ki - kj - kk - kl - km - kn - ko - kr - ks - ku - kv - kw - ky - la - lb - lg - li - ln - lo - lt - lu - lv - mg - mh - mi - mk - ml - mn - mr - ms - mt - my - na - nb - nd - ne - ng - nl - nn - 'no' - nr - nv - ny - oc - oj - om - or - os - pa - pi - pl - ps - pt - qu - rm - rn - ro - ru - rw - sa - sc - sd - se - sg - si - sk - sl - sm - sn - so - sq - sr - ss - st - su - sv - sw - ta - te - tg - th - ti - tk - tl - tn - to - tr - ts - tt - tw - ty - ug - uk - ur - uz - ve - vi - vo - wa - wo - xh - yi - yue - yo - za - zh - zu title: ISO 639-1 Language Code - type: string enum: - auto title: Auto-detect chunkPlan: description: >- This is the plan for chunking the model output before it is sent to the voice provider. allOf: - $ref: '#/components/schemas/ChunkPlan' required: - provider - voiceId FallbackOpenAIVoice: type: object properties: cachingEnabled: type: boolean description: This is the flag to toggle voice caching for the assistant. example: true default: true provider: type: string description: This is the voice provider that will be used. enum: - openai voiceId: description: >- This is the provider-specific ID that will be used. Please note that ash, ballad, coral, sage, and verse may only be used with realtime models. oneOf: - type: string enum: - alloy - echo - fable - onyx - nova - shimmer title: Preset Voice Options - type: string title: OpenAI Voice ID model: type: string description: This is the model that will be used for text-to-speech. enum: - tts-1 - tts-1-hd - gpt-4o-mini-tts instructions: type: string description: >- This is a prompt that allows you to control the voice of your generated audio. Does not work with 'tts-1' or 'tts-1-hd' models. maxLength: 10000 speed: type: number description: This is the speed multiplier that will be used. minimum: 0.25 maximum: 4 example: null chunkPlan: description: >- This is the plan for chunking the model output before it is sent to the voice provider. allOf: - $ref: '#/components/schemas/ChunkPlan' required: - provider - voiceId FallbackPlayHTVoice: type: object properties: cachingEnabled: type: boolean description: This is the flag to toggle voice caching for the assistant. example: true default: true provider: type: string description: This is the voice provider that will be used. enum: - playht voiceId: description: This is the provider-specific ID that will be used. oneOf: - type: string enum: - jennifer - melissa - will - chris - matt - jack - ruby - davis - donna - michael title: Preset Voice Options - type: string title: PlayHT Voice ID speed: type: number description: This is the speed multiplier that will be used. minimum: 0.1 maximum: 5 example: null temperature: type: number description: >- A floating point number between 0, exclusive, and 2, inclusive. If equal to null or not provided, the model's default temperature will be used. The temperature parameter controls variance. Lower temperatures result in more predictable results, higher temperatures allow each run to vary more, so the voice may sound less like the baseline voice. minimum: 0.1 maximum: 2 example: null emotion: type: string description: An emotion to be applied to the speech. enum: - female_happy - female_sad - female_angry - female_fearful - female_disgust - female_surprised - male_happy - male_sad - male_angry - male_fearful - male_disgust - male_surprised example: null voiceGuidance: type: number description: >- A number between 1 and 6. Use lower numbers to reduce how unique your chosen voice will be compared to other voices. minimum: 1 maximum: 6 example: null styleGuidance: type: number description: >- A number between 1 and 30. Use lower numbers to to reduce how strong your chosen emotion will be. Higher numbers will create a very emotional performance. minimum: 1 maximum: 30 example: null textGuidance: type: number description: >- A number between 1 and 2. This number influences how closely the generated speech adheres to the input text. Use lower values to create more fluid speech, but with a higher chance of deviating from the input text. Higher numbers will make the generated speech more accurate to the input text, ensuring that the words spoken align closely with the provided text. minimum: 1 maximum: 2 example: null model: type: string description: Playht voice model/engine to use. enum: - PlayHT2.0 - PlayHT2.0-turbo - Play3.0-mini - PlayDialog language: type: string description: The language to use for the speech. enum: - afrikaans - albanian - amharic - arabic - bengali - bulgarian - catalan - croatian - czech - danish - dutch - english - french - galician - german - greek - hebrew - hindi - hungarian - indonesian - italian - japanese - korean - malay - mandarin - polish - portuguese - russian - serbian - spanish - swedish - tagalog - thai - turkish - ukrainian - urdu - xhosa chunkPlan: description: >- This is the plan for chunking the model output before it is sent to the voice provider. allOf: - $ref: '#/components/schemas/ChunkPlan' required: - provider - voiceId FallbackRimeAIVoice: type: object properties: cachingEnabled: type: boolean description: This is the flag to toggle voice caching for the assistant. example: true default: true provider: type: string description: This is the voice provider that will be used. enum: - rime-ai voiceId: description: This is the provider-specific ID that will be used. oneOf: - type: string enum: - abbie - allison - ally - alona - amber - ana - antoine - armon - brenda - brittany - carol - colin - courtney - elena - elliot - eva - geoff - gerald - hank - helen - hera - jen - joe - joy - juan - kendra - kendrick - kenneth - kevin - kris - linda - madison - marge - marina - marissa - marta - maya - nicholas - nyles - phil - reba - rex - rick - ritu - rob - rodney - rohan - rosco - samantha - sandy - selena - seth - sharon - stan - tamra - tanya - tibur - tj - tyler - viv - yadira - marsh - bayou - creek - brook - flower - spore - glacier - gulch - alpine - cove - lagoon - tundra - steppe - mesa - grove - rainforest - moraine - wildflower - peak - boulder - gypsum - zest - luna - celeste - orion - ursa - astra - esther - estelle - andromeda title: Preset Voice Options - type: string title: RimeAI Voice ID model: type: string description: >- This is the model that will be used. Defaults to 'mistv2' when not specified. enum: - mist - mistv2 - arcana example: mistv2 speed: type: number description: This is the speed multiplier that will be used. minimum: 0.1 example: null pauseBetweenBrackets: type: boolean description: >- This is a flag that controls whether to add slight pauses using angle brackets. Example: "Hi. <200> I'd love to have a conversation with you." adds a 200ms pause between the first and second sentences. example: false phonemizeBetweenBrackets: type: boolean description: >- This is a flag that controls whether text inside brackets should be phonemized (converted to phonetic pronunciation) - Example: "{h'El.o} World" will pronounce "Hello" as expected. example: false reduceLatency: type: boolean description: >- This is a flag that controls whether to optimize for reduced latency in streaming. https://docs.rime.ai/api-reference/endpoint/websockets#param-reduce-latency example: false inlineSpeedAlpha: type: string description: >- This is a string that allows inline speed control using alpha notation. https://docs.rime.ai/api-reference/endpoint/websockets#param-inline-speed-alpha example: null chunkPlan: description: >- This is the plan for chunking the model output before it is sent to the voice provider. allOf: - $ref: '#/components/schemas/ChunkPlan' required: - provider - voiceId FallbackSmallestAIVoice: type: object properties: cachingEnabled: type: boolean description: This is the flag to toggle voice caching for the assistant. example: true default: true provider: type: string description: This is the voice provider that will be used. enum: - smallest-ai voiceId: description: This is the provider-specific ID that will be used. oneOf: - type: string enum: - emily - jasmine - arman - james - mithali - aravind - raj - diya - raman - ananya - isha - william - aarav - monika - niharika - deepika - raghav - kajal - radhika - mansi - nisha - saurabh - pooja - saina - sanya title: Preset Voice Options - type: string title: Smallest AI Voice ID model: type: string description: >- Smallest AI voice model to use. Defaults to 'lightning' when not specified. enum: - lightning speed: type: number description: This is the speed multiplier that will be used. example: null chunkPlan: description: >- This is the plan for chunking the model output before it is sent to the voice provider. allOf: - $ref: '#/components/schemas/ChunkPlan' required: - provider - voiceId FallbackTavusVoice: type: object properties: cachingEnabled: type: boolean description: This is the flag to toggle voice caching for the assistant. example: true default: true provider: type: string description: This is the voice provider that will be used. enum: - tavus voiceId: description: This is the provider-specific ID that will be used. oneOf: - type: string enum: - r52da2535a title: Preset Voice Options - type: string title: Tavus Voice ID personaId: type: string description: >- This is the unique identifier for the persona that the replica will use in the conversation. callbackUrl: type: string description: >- This is the url that will receive webhooks with updates regarding the conversation state. conversationName: type: string description: This is the name for the conversation. conversationalContext: type: string description: >- This is the context that will be appended to any context provided in the persona, if one is provided. customGreeting: type: string description: >- This is the custom greeting that the replica will give once a participant joines the conversation. properties: description: These are optional properties used to customize the conversation. allOf: - $ref: '#/components/schemas/TavusConversationProperties' chunkPlan: description: >- This is the plan for chunking the model output before it is sent to the voice provider. allOf: - $ref: '#/components/schemas/ChunkPlan' required: - provider - voiceId FallbackNeuphonicVoice: type: object properties: cachingEnabled: type: boolean description: This is the flag to toggle voice caching for the assistant. example: true default: true provider: type: string description: This is the voice provider that will be used. enum: - neuphonic voiceId: description: This is the provider-specific ID that will be used. oneOf: - type: string enum: - test title: Preset Voice Options - type: string title: Neuphonic Voice ID model: type: string description: >- This is the model that will be used. Defaults to 'neu_fast' if not specified. enum: - neu_hq - neu_fast example: neu_fast language: type: object description: This is the language (ISO 639-1) that is enforced for the model. example: en speed: type: number description: This is the speed multiplier that will be used. minimum: 0.25 maximum: 2 example: null chunkPlan: description: >- This is the plan for chunking the model output before it is sent to the voice provider. allOf: - $ref: '#/components/schemas/ChunkPlan' required: - provider - voiceId - language FallbackSesameVoice: type: object properties: cachingEnabled: type: boolean description: This is the flag to toggle voice caching for the assistant. example: true default: true provider: type: string description: This is the voice provider that will be used. enum: - sesame voiceId: type: string description: This is the provider-specific ID that will be used. title: >- Sesame Voice ID. This should be either a name (a built-in voice) or a UUID (a custom voice). model: type: string description: This is the model that will be used. enum: - csm-1b chunkPlan: description: >- This is the plan for chunking the model output before it is sent to the voice provider. allOf: - $ref: '#/components/schemas/ChunkPlan' required: - provider - voiceId - model FallbackInworldVoice: type: object properties: cachingEnabled: type: boolean description: This is the flag to toggle voice caching for the assistant. example: true default: true provider: type: string description: This is the voice provider that will be used. enum: - inworld voiceId: type: string description: >- Available voices by language: • en: Alex, Ashley, Craig, Deborah, Dennis, Edward, Elizabeth, Hades, Julia, Pixie, Mark, Olivia, Priya, Ronald, Sarah, Shaun, Theodore, Timothy, Wendy, Dominus • zh: Yichen, Xiaoyin, Xinyi, Jing • nl: Erik, Katrien, Lennart, Lore • fr: Alain, Hélène, Mathieu, Étienne • de: Johanna, Josef • it: Gianni, Orietta • ja: Asuka, Satoshi • ko: Hyunwoo, Minji, Seojun, Yoona • pl: Szymon, Wojciech • pt: Heitor, Maitê • es: Diego, Lupita, Miguel, Rafael maxLength: 120 title: Inworld Voice ID enum: - Alex - Ashley - Craig - Deborah - Dennis - Edward - Elizabeth - Hades - Julia - Pixie - Mark - Olivia - Priya - Ronald - Sarah - Shaun - Theodore - Timothy - Wendy - Dominus - Yichen - Xiaoyin - Xinyi - Jing - Erik - Katrien - Lennart - Lore - Alain - Hélène - Mathieu - Étienne - Johanna - Josef - Gianni - Orietta - Asuka - Satoshi - Hyunwoo - Minji - Seojun - Yoona - Szymon - Wojciech - Heitor - Maitê - Diego - Lupita - Miguel - Rafael example: Alex model: type: string description: This is the model that will be used. enum: - inworld-tts-1 default: inworld-tts-1 languageCode: type: string description: Language code for Inworld TTS synthesis default: en enum: - en - zh - ko - nl - fr - es - ja - de - it - pl - pt chunkPlan: description: >- This is the plan for chunking the model output before it is sent to the voice provider. allOf: - $ref: '#/components/schemas/ChunkPlan' required: - provider - voiceId SipTrunkOutboundSipRegisterPlan: type: object properties: domain: type: string username: type: string realm: type: string RegexOption: type: object properties: type: type: string description: |- This is the type of the regex option. Options are: - `ignore-case`: Ignores the case of the text being matched. Add - `whole-word`: Matches whole words only. - `multi-line`: Matches across multiple lines. enum: - ignore-case - whole-word - multi-line enabled: type: boolean description: |- This is whether to enable the option. @default false required: - type - enabled TextContent: type: object properties: type: type: string enum: - text text: type: string language: type: string enum: - aa - ab - ae - af - ak - am - an - ar - as - av - ay - az - ba - be - bg - bh - bi - bm - bn - bo - br - bs - ca - ce - ch - co - cr - cs - cu - cv - cy - da - de - dv - dz - ee - el - en - eo - es - et - eu - fa - ff - fi - fj - fo - fr - fy - ga - gd - gl - gn - gu - gv - ha - he - hi - ho - hr - ht - hu - hy - hz - ia - id - ie - ig - ii - ik - io - is - it - iu - ja - jv - ka - kg - ki - kj - kk - kl - km - kn - ko - kr - ks - ku - kv - kw - ky - la - lb - lg - li - ln - lo - lt - lu - lv - mg - mh - mi - mk - ml - mn - mr - ms - mt - my - na - nb - nd - ne - ng - nl - nn - 'no' - nr - nv - ny - oc - oj - om - or - os - pa - pi - pl - ps - pt - qu - rm - rn - ro - ru - rw - sa - sc - sd - se - sg - si - sk - sl - sm - sn - so - sq - sr - ss - st - su - sv - sw - ta - te - tg - th - ti - tk - tl - tn - to - tr - ts - tt - tw - ty - ug - uk - ur - uz - ve - vi - vo - wa - wo - xh - yi - yue - yo - za - zh - zu required: - type - text - language Condition: type: object properties: operator: type: string description: >- This is the operator you want to use to compare the parameter and value. enum: - eq - neq - gt - gte - lt - lte param: type: string description: This is the name of the parameter that you want to check. maxLength: 1000 value: type: string description: This is the value you want to compare against the parameter. maxLength: 1000 required: - operator - param - value VariableExtractionAlias: type: object properties: key: type: string description: >- This is the key of the variable. This variable will be accessible during the call as `{{key}}` and stored in `call.artifact.variableValues` after the call. Rules: - Must start with a letter (a-z, A-Z). - Subsequent characters can be letters, numbers, or underscores. - Minimum length of 1 and maximum length of 40. minLength: 1 maxLength: 40 pattern: /^[a-zA-Z][a-zA-Z0-9_]*$/ value: type: string description: >- This is the value of the variable. This can reference existing variables, use filters, and perform transformations. Examples: "{{name}}", "{{customer.email}}", "Hello {{name | upcase}}" maxLength: 10000 required: - key - value OpenAIFunctionParameters: type: object properties: type: type: string description: >- This must be set to 'object'. It instructs the model to return a JSON object containing the function call properties. enum: - object properties: type: object description: >- This provides a description of the properties required by the function. JSON Schema can be used to specify expectations for each property. Refer to [this doc](https://ajv.js.org/json-schema.html#json-data-type) for a comprehensive guide on JSON Schema. additionalProperties: $ref: '#/components/schemas/JsonSchema' required: description: This specifies the properties that are required by the function. type: array items: type: string required: - type - properties CustomMessage: type: object properties: contents: type: array description: >- This is an alternative to the `content` property. It allows to specify variants of the same content, one per language. Usage: - If your assistants are multilingual, you can provide content for each language. - If you don't provide content for a language, the first item in the array will be automatically translated to the active language at that moment. This will override the `content` property. items: oneOf: - $ref: '#/components/schemas/TextContent' title: Text type: type: string description: This is a custom message. enum: - custom-message content: type: string description: >- This is the content that the assistant will say when this message is triggered. maxLength: 1000 required: - type TransferPlan: type: object properties: mode: type: string description: >- This configures how transfer is executed and the experience of the destination party receiving the call. Usage: - `blind-transfer`: The assistant forwards the call to the destination without any message or summary. - `blind-transfer-add-summary-to-sip-header`: The assistant forwards the call to the destination and adds a SIP header X-Transfer-Summary to the call to include the summary. - `warm-transfer-say-message`: The assistant dials the destination, delivers the `message` to the destination party, connects the customer, and leaves the call. - `warm-transfer-say-summary`: The assistant dials the destination, provides a summary of the call to the destination party, connects the customer, and leaves the call. - `warm-transfer-wait-for-operator-to-speak-first-and-then-say-message`: The assistant dials the destination, waits for the operator to speak, delivers the `message` to the destination party, and then connects the customer. - `warm-transfer-wait-for-operator-to-speak-first-and-then-say-summary`: The assistant dials the destination, waits for the operator to speak, provides a summary of the call to the destination party, and then connects the customer. - `warm-transfer-twiml`: The assistant dials the destination, executes the twiml instructions on the destination call leg, connects the customer, and leaves the call. - `warm-transfer-experimental`: The assistant puts the customer on hold, dials the destination, and if the destination answers (and is human), delivers a message or summary before connecting the customer. If the destination is unreachable or not human (e.g., with voicemail detection), the assistant delivers the `fallbackMessage` to the customer and optionally ends the call. @default 'blind-transfer' enum: - blind-transfer - blind-transfer-add-summary-to-sip-header - warm-transfer-say-message - warm-transfer-say-summary - warm-transfer-twiml - >- warm-transfer-wait-for-operator-to-speak-first-and-then-say-message - >- warm-transfer-wait-for-operator-to-speak-first-and-then-say-summary - warm-transfer-experimental message: description: >- This is the message the assistant will deliver to the destination party before connecting the customer. Usage: - Used only when `mode` is `blind-transfer-add-summary-to-sip-header`, `warm-transfer-say-message`, `warm-transfer-wait-for-operator-to-speak-first-and-then-say-message`, or `warm-transfer-experimental`. oneOf: - type: string - $ref: '#/components/schemas/CustomMessage' timeout: type: number description: >- This is the timeout in seconds for the warm-transfer-wait-for-operator-to-speak-first-and-then-say-message/summary @default 60 minimum: 1 maximum: 600 default: 60 sipVerb: type: object description: |- This specifies the SIP verb to use while transferring the call. - 'refer': Uses SIP REFER to transfer the call (default) - 'bye': Ends current call with SIP BYE - 'dial': Uses SIP DIAL to transfer the call default: refer enum: - refer - bye - dial holdAudioUrl: type: string description: >- This is the URL to an audio file played while the customer is on hold during transfer. Usage: - Used only when `mode` is `warm-transfer-experimental`. - Used when transferring calls to play hold audio for the customer. - Must be a publicly accessible URL to an audio file. - Supported formats: MP3 and WAV. - If not provided, the default hold audio will be used. transferCompleteAudioUrl: type: string description: >- This is the URL to an audio file played after the warm transfer message or summary is delivered to the destination party. It can be used to play a custom sound like 'beep' to notify that the transfer is complete. Usage: - Used only when `mode` is `warm-transfer-experimental`. - Used when transferring calls to play hold audio for the destination party. - Must be a publicly accessible URL to an audio file. - Supported formats: MP3 and WAV. twiml: type: string description: >- This is the TwiML instructions to execute on the destination call leg before connecting the customer. Usage: - Used only when `mode` is `warm-transfer-twiml`. - Supports only `Play`, `Say`, `Gather`, `Hangup` and `Pause` verbs. - Maximum length is 4096 characters. Example: ``` Hello, transferring a customer to you. They called about billing questions. ``` maxLength: 4096 summaryPlan: description: >- This is the plan for generating a summary of the call to present to the destination party. Usage: - Used only when `mode` is `blind-transfer-add-summary-to-sip-header` or `warm-transfer-say-summary` or `warm-transfer-wait-for-operator-to-speak-first-and-then-say-summary` or `warm-transfer-experimental`. allOf: - $ref: '#/components/schemas/SummaryPlan' sipHeadersInReferToEnabled: type: boolean description: >- This flag includes the sipHeaders from above in the refer to sip uri as url encoded query params. @default false fallbackPlan: description: >- This configures the fallback plan when the transfer fails (destination unreachable, busy, or not human). Usage: - Used only when `mode` is `warm-transfer-experimental`. - If not provided when using `warm-transfer-experimental`, a default message will be used. allOf: - $ref: '#/components/schemas/TransferFallbackPlan' required: - mode GeminiMultimodalLiveVoiceConfig: type: object properties: prebuiltVoiceConfig: $ref: '#/components/schemas/GeminiMultimodalLivePrebuiltVoiceConfig' required: - prebuiltVoiceConfig ExactReplacement: type: object properties: type: type: string description: >- This is the exact replacement type. You can use this to replace a specific word or phrase with a different word or phrase. Usage: - Replace "hello" with "hi": { type: 'exact', key: 'hello', value: 'hi' } - Replace "good morning" with "good day": { type: 'exact', key: 'good morning', value: 'good day' } - Replace a specific name: { type: 'exact', key: 'John Doe', value: 'Jane Smith' } - Replace an acronym: { type: 'exact', key: 'AI', value: 'Artificial Intelligence' } - Replace a company name with its phonetic pronunciation: { type: 'exact', key: 'cozmox', value: 'Vappy' } enum: - exact replaceAllEnabled: type: boolean description: >- This option let's you control whether to replace all instances of the key or only the first one. By default, it only replaces the first instance. Examples: - For { type: 'exact', key: 'hello', value: 'hi', replaceAllEnabled: false }. Before: "hello world, hello universe" | After: "hi world, hello universe" - For { type: 'exact', key: 'hello', value: 'hi', replaceAllEnabled: true }. Before: "hello world, hello universe" | After: "hi world, hi universe" @default false default: false key: type: string description: This is the key to replace. value: type: string description: This is the value that will replace the match. maxLength: 1000 required: - type - key - value RegexReplacement: type: object properties: type: type: string description: >- This is the regex replacement type. You can use this to replace a word or phrase that matches a pattern. Usage: - Replace all numbers with "some number": { type: 'regex', regex: '\\d+', value: 'some number' } - Replace email addresses with "[EMAIL]": { type: 'regex', regex: '\\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\\.[A-Z|a-z]{2,}\\b', value: '[EMAIL]' } - Replace phone numbers with a formatted version: { type: 'regex', regex: '(\\d{3})(\\d{3})(\\d{4})', value: '($1) $2-$3' } - Replace all instances of "color" or "colour" with "hue": { type: 'regex', regex: 'colou?r', value: 'hue' } - Capitalize the first letter of every sentence: { type: 'regex', regex: '(?<=\\. |^)[a-z]', value: (match) => match.toUpperCase() } enum: - regex regex: type: string description: >- This is the regex pattern to replace. Note: - This works by using the `string.replace` method in Node.JS. Eg. `"hello there".replace(/hello/g, "hi")` will return `"hi there"`. Hot tip: - In JavaScript, escape `\` when sending the regex pattern. Eg. `"hello\sthere"` will be sent over the wire as `"hellosthere"`. Send `"hello\\sthere"` instead. options: description: >- These are the options for the regex replacement. Defaults to all disabled. @default [] type: array items: $ref: '#/components/schemas/RegexOption' value: type: string description: This is the value that will replace the match. maxLength: 1000 required: - type - regex - value TransferFallbackPlan: type: object properties: message: description: >- This is the message the assistant will deliver to the customer if the transfer fails. oneOf: - type: string - $ref: '#/components/schemas/CustomMessage' endCallEnabled: type: boolean description: >- This controls what happens after delivering the failure message to the customer. - true: End the call after delivering the failure message (default) - false: Keep the assistant on the call to continue handling the customer's request @default true default: true required: - message GeminiMultimodalLivePrebuiltVoiceConfig: type: object properties: voiceName: type: string enum: - Puck - Charon - Kore - Fenrir - Aoede required: - voiceName securitySchemes: bearer: scheme: bearer bearerFormat: Bearer type: http description: Retrieve your API Key from [Dashboard](dashboard.cozmox.ai). ````